CN113538396B

CN113538396B - Counting prompting method and device based on injection needle processing

Info

Publication number: CN113538396B
Application number: CN202110853867.1A
Authority: CN
Inventors: 祁建忠; 康传清; 谭伟
Original assignee: Yangzhou Medline Industry Co ltd
Current assignee: Yangzhou Meilai Medical Supplies Co ltd
Priority date: 2021-07-27
Filing date: 2021-07-27
Publication date: 2022-04-26
Anticipated expiration: 2041-07-27
Also published as: CN113538396A

Abstract

The invention discloses a counting prompting method and a device based on injection needle processing, wherein the method comprises the following steps: obtaining the first product characteristic through the first characteristic extraction instruction; obtaining an image including the first tool position without a product through the first image acquisition device; further obtaining a first convolution characteristic; obtaining a first image segmentation result according to the first image segmentation instruction; performing feature traversal on the first image segmentation result based on the first convolution feature to obtain a first feature traversal result; and judging whether the first product exists in the first image or not, if so, obtaining a first counting instruction, and counting the first product existing in the first tooling position through a counting device. The technical problem that the actual processing quantity of the injection needles cannot be monitored in real time and counted in the prior art is solved. The technical effects of monitoring the processing process of the injection needles in real time and accurately recording the actual processing quantity of the injection needles are achieved.

Description

Counting prompting method and device based on injection needle processing

Technical Field

The invention relates to the field of artificial intelligence, in particular to a counting prompting method and device based on injection needle processing.

Background

In the process of diagnosing and treating human diseases, the medical instrument can be an important tool for diagnosing and treating diseases because the limitation of the capability of medical workers can be made up, and plays a vital role in the actual diagnosis and treatment process, wherein the medical injection needle is a common instrument in the modern medical diagnosis and treatment process. Along with the continuous improvement of the manufacturing level of China, the process of manufacturing the injection needle which is originally complex and difficult to control is greatly simplified, the production efficiency is also improved, and meanwhile, the efficiency of manufacturing and processing the injection needle by enterprises can also be greatly improved by researching and developing an intelligent device.

In the process of implementing the technical scheme of the invention in the embodiment of the present application, the inventor of the present application finds that the above-mentioned technology has at least the following technical problems:

the technical problem that the actual processing quantity of the injection needles cannot be monitored and counted in real time, and the production and processing progress of the injection needles cannot be accurately grasped exists in the prior art.

Disclosure of Invention

In view of this, the present application provides a counting indication method based on needle processing, where the method includes: obtaining a first image through the first image acquisition device, wherein the first image is an image comprising a first tooling position; obtaining information of a first product, wherein the first product is a product which is currently subjected to injection needle processing; obtaining a first feature extraction instruction, and performing product feature extraction on the first product according to the first feature extraction instruction to obtain a first product feature; obtaining a second image through the first image acquisition device, wherein the second image comprises an image of the first tooling position when no product exists; according to the second image and the first product characteristics, distinguishing characteristic extraction is carried out, and first volume characteristics are obtained based on a distinguishing characteristic extraction result; obtaining a first image segmentation instruction, and performing image segmentation on the first image according to the first image segmentation instruction to obtain a first image segmentation result; performing feature traversal on the first image segmentation result based on the first convolution feature to obtain a first feature traversal result; judging whether the first product exists in the first image or not based on the first feature traversal result to obtain a first judgment result; when the first judgment result is that the first image contains the first product, obtaining a first counting instruction; and counting the first products existing in the first tooling position through the first counting device according to the first counting instruction. The technical problem of exist among the prior art unable real-time supervision and make statistics of syringe needle actual processing quantity, lead to unable accurate assurance syringe needle production and processing progress is solved. The real-time monitoring syringe needle course of working, the actual processing quantity of accurate record syringe needle have been reached, have further improved the production and processing syringe needle efficiency of enterprise, hold the technical effect of syringe needle processing progress accurately.

In view of the above problems, the embodiments of the present application provide a method and an apparatus for presenting a count based on needle processing.

In a first aspect, the present application provides a method for counting and prompting based on needle processing, which is implemented by a counting and prompting device based on needle processing, wherein the method comprises: obtaining a first image through the first image acquisition device, wherein the first image is an image comprising a first tooling position; obtaining information of a first product, wherein the first product is a product which is currently subjected to injection needle processing; obtaining a first feature extraction instruction, and performing product feature extraction on the first product according to the first feature extraction instruction to obtain a first product feature; obtaining a second image through the first image acquisition device, wherein the second image comprises an image of the first tooling position when no product exists; according to the second image and the first product characteristics, distinguishing characteristic extraction is carried out, and first volume characteristics are obtained based on a distinguishing characteristic extraction result; obtaining a first image segmentation instruction, and performing image segmentation on the first image according to the first image segmentation instruction to obtain a first image segmentation result; performing feature traversal on the first image segmentation result based on the first convolution feature to obtain a first feature traversal result; judging whether the first product exists in the first image or not based on the first feature traversal result to obtain a first judgment result; when the first judgment result is that the first image contains the first product, obtaining a first counting instruction; and counting the first products existing in the first tooling position through the first counting device according to the first counting instruction.

In another aspect, the present application further provides a counting and prompting device based on needle processing, for performing the counting and prompting method based on needle processing according to the first aspect, the device is communicatively connected to a first image acquisition device and a first counting device, wherein the device includes: a first obtaining unit: the first obtaining unit is used for obtaining a first image through the first image acquisition device, wherein the first image is an image comprising a first tooling position; a second obtaining unit: the second obtaining unit is used for obtaining information of a first product, wherein the first product is a product which is currently processed by the injection needle; a third obtaining unit: the third obtaining unit is used for obtaining a first feature extraction instruction, and performing feature extraction on the first product according to the first feature extraction instruction to obtain a first product feature; a fourth obtaining unit: the fourth obtaining unit is used for obtaining a second image through the first image acquisition device, wherein the second image comprises an image of the first tooling position when no product exists; a fifth obtaining unit: the fifth obtaining unit is used for performing distinguishing feature extraction according to the second image and the first product feature, and obtaining a first convolution feature based on a distinguishing feature extraction result; a sixth obtaining unit: the sixth obtaining unit is configured to obtain a first image segmentation instruction, perform image segmentation on the first image according to the first image segmentation instruction, and obtain a first image segmentation result; a seventh obtaining unit: the seventh obtaining unit is configured to perform feature traversal on the first image segmentation result based on the first convolution feature to obtain a first feature traversal result; an eighth obtaining unit: the eighth obtaining unit is configured to determine whether the first product exists in the first image based on the first feature traversal result, and obtain a first determination result; a ninth obtaining unit: the ninth obtaining unit is configured to obtain a first counting instruction when the first determination result indicates that the first image includes the first product; a first counting unit: the first counting unit is used for counting the first products existing in the first tooling position through the first counting device according to the first counting instruction.

In a third aspect, an embodiment of the present application further provides a counting and prompting device based on needle processing, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method according to the first aspect when executing the program.

One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

1. obtaining a first image through the first image acquisition device, wherein the first image is an image comprising a first tooling position; obtaining information of a first product, wherein the first product is a product which is currently subjected to injection needle processing; obtaining a first feature extraction instruction, and performing product feature extraction on the first product according to the first feature extraction instruction to obtain a first product feature; obtaining a second image through the first image acquisition device, wherein the second image comprises an image of the first tooling position when no product exists; according to the second image and the first product characteristics, distinguishing characteristic extraction is carried out, and first volume characteristics are obtained based on a distinguishing characteristic extraction result; obtaining a first image segmentation instruction, and performing image segmentation on the first image according to the first image segmentation instruction to obtain a first image segmentation result; performing feature traversal on the first image segmentation result based on the first convolution feature to obtain a first feature traversal result; judging whether the first product exists in the first image or not based on the first feature traversal result to obtain a first judgment result; when the first judgment result is that the first image contains the first product, obtaining a first counting instruction; and counting the first products existing in the first tooling position through the first counting device according to the first counting instruction. The real-time monitoring syringe needle course of working, the actual processing quantity of accurate record syringe needle have been reached, have further improved the production and processing syringe needle efficiency of enterprise, hold the technical effect of syringe needle processing progress accurately.

2. The feature extraction model established on the basis of the neural network model can output accurate convolution feature information, so that the method has strong analysis and calculation capacity, achieves the technical effects of accurately obtaining data information and improving the intellectualization of evaluation results.

3. Through combining syringe needle processing count with the digital mode at present, improved the device and detected the rate of accuracy of occupy-place product, reached the accuracy of having guaranteed device processing count, intelligent management production and processing has beaten the technological effect of corresponding technological basis for the machining efficiency maximize of enterprise.

The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.

Drawings

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

Fig. 1 is a schematic flowchart of a counting prompting method based on injection needle processing according to an embodiment of the present application;

fig. 2 is a schematic structural diagram of a counting prompting device based on injection needle processing according to an embodiment of the present application;

fig. 3 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.

Description of reference numerals:

a first obtaining unit 11, a second obtaining unit 12, a third obtaining unit 13, a fourth obtaining unit 14, a fifth obtaining unit 15, a sixth obtaining unit 16, a seventh obtaining unit 17, an eighth obtaining unit 18, a ninth obtaining unit 19, a first counting unit 20, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, and a bus interface 305.

Detailed Description

The embodiment of the application provides a counting prompt method and device based on injection needle processing, and solves the technical problem that the injection needle production and processing progress cannot be accurately grasped due to the fact that the injection needle actual processing quantity cannot be monitored and counted in real time in the prior art. The real-time monitoring syringe needle course of working, the actual processing quantity of accurate record syringe needle have been reached, have further improved the production and processing syringe needle efficiency of enterprise, hold the technical effect of syringe needle processing progress accurately.

In the following, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings, and it is to be understood that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application. It should be further noted that, for the convenience of description, only some but not all of the elements relevant to the present application are shown in the drawings.

Summary of the application

In the process of diagnosing and treating human diseases, the medical instrument can be an important tool for diagnosing and treating diseases because the limitation of the capability of medical workers can be made up, and plays a vital role in the actual diagnosis and treatment process, wherein the medical injection needle is a common instrument in the modern medical diagnosis and treatment process. Along with the continuous improvement of the manufacturing level of China, the process of manufacturing the injection needle which is originally complex and difficult to control is greatly simplified, the production efficiency is also improved, and meanwhile, the efficiency of manufacturing and processing the injection needle by enterprises can also be greatly improved by researching and developing an intelligent device. The technical problem that the actual processing quantity of the injection needles cannot be monitored and counted in real time, and the production and processing progress of the injection needles cannot be accurately grasped exists in the prior art.

In view of the above technical problems, the technical solution provided by the present application has the following general idea:

the application provides a counting prompting method based on injection needle processing, which is applied to a counting prompting device based on injection needle processing, wherein the method comprises the following steps: obtaining a first image through the first image acquisition device, wherein the first image is an image comprising a first tooling position; obtaining information of a first product, wherein the first product is a product which is currently subjected to injection needle processing; obtaining a first feature extraction instruction, and performing product feature extraction on the first product according to the first feature extraction instruction to obtain a first product feature; obtaining a second image through the first image acquisition device, wherein the second image comprises an image of the first tooling position when no product exists; according to the second image and the first product characteristics, distinguishing characteristic extraction is carried out, and first volume characteristics are obtained based on a distinguishing characteristic extraction result; obtaining a first image segmentation instruction, and performing image segmentation on the first image according to the first image segmentation instruction to obtain a first image segmentation result; performing feature traversal on the first image segmentation result based on the first convolution feature to obtain a first feature traversal result; judging whether the first product exists in the first image or not based on the first feature traversal result to obtain a first judgment result; when the first judgment result is that the first image contains the first product, obtaining a first counting instruction; and counting the first products existing in the first tooling position through the first counting device according to the first counting instruction.

Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.

Example one

Referring to fig. 1, an embodiment of the present application provides a counting prompting method based on needle processing, where the method is applied to an intelligent counting device, the device is in communication connection with a first image acquisition device and a first counting device, and the method specifically includes the following steps:

step S100: obtaining a first image through the first image acquisition device, wherein the first image is an image comprising a first tooling position;

specifically, the injection needle refers to a needle used in combination with a medical device such as an injector for injecting liquid or gas into a human body to achieve the purpose of diagnosis, treatment and disease prevention. The embodiment of the application provides a counting prompting method based on injection needle processing, wherein the method is applied to a counting prompting device based on injection needle processing, and the device is in communication connection with a first image acquisition device and a first counting device. The first image acquisition device is equipment capable of acquiring images in real time, and can be camera equipment and the like, and the first counting device is a device capable of counting the number of pulses in real time, so that the functions of measurement, counting and control are realized. The first image acquisition device acquires a first image, the first image refers to images of all configuration environments including a tool position and the vicinity of the tool position, the tool position refers to a component of process equipment for processing an injection needle, the first image acquisition device acquires the image of the first tool position, the first image refers to images of all configuration environments including the tool position and the vicinity of the tool position, and the first image real-time acquisition device provides a basis for accurately distinguishing whether a product is tamped in the current tool position or not.

Step S200: obtaining information of a first product, wherein the first product is a product which is currently subjected to injection needle processing;

step S300: obtaining a first feature extraction instruction, and performing product feature extraction on the first product according to the first feature extraction instruction to obtain a first product feature;

specifically, the first product, i.e. the injection needle to be processed, refers to the product currently processed by the injection needle. The information of the first product refers to all information of the product currently subjected to the injection needle processing. Product information includes model, pinhole, internal diameter size, the exposure needle of syringe needle length, needle file size and colour etc. basic characteristic parameter information, first characteristic extraction instruction by the counting assembly of syringe needle processing sends, through first characteristic extraction instruction device is right promptly by oneself first product carries out the characteristic extraction of product, the characteristic extraction process of product is through extracting the characteristic of product, is convenient for carry out the means of the identification of product, extracts the most representative product position is selected as the product characteristic in the first product through the characteristic to the product, for follow-up can be accurate distinguish the product, tamps the basis to the accurate count of product.

Step S400: obtaining a second image through the first image acquisition device, wherein the second image comprises an image of the first tooling position when no product exists;

specifically, the second image is an image obtained when there is no injection needle being processed at the tool position. And acquiring an image of the first tooling position through the first image acquisition device to obtain the second image, wherein the second image can be an image set, and acquiring the image of the first tooling position when no product exists through the first image acquisition device to obtain the image set.

Step S500: according to the second image and the first product characteristics, distinguishing characteristic extraction is carried out, and first volume characteristics are obtained based on a distinguishing characteristic extraction result;

specifically, the second image refers to an image of a tool position; the first product characteristic is the needle head characteristic of the processed injection needle and is obtained by analyzing the tool position and extracting the images of the area near the tool position. Through to containing the second image of the characteristic of first frock position with first product feature carries out the comparison of characteristic, obtains to detect out more easily whether first frock position has the distinguishing feature of product information, will distinguishing feature is as first convolution feature, through the second image is to first product feature contrasts, obtains more representative first convolution feature, can be right whether there is the product in first frock position carries out more accurate analysis and judgement, for follow-up accurate count that carries on the product has laid the foundation.

Step S600: obtaining a first image segmentation instruction, and performing image segmentation on the first image according to the first image segmentation instruction to obtain a first image segmentation result;

step S700: performing feature traversal on the first image segmentation result based on the first convolution feature to obtain a first feature traversal result;

specifically, the first image division command is issued by a count presentation device for needle processing when the first image is obtained. And according to the first image segmentation instruction, segmenting the first image according to 5 pixels by 5 pixels, and obtaining a small region after segmenting the first image of a plurality of 5 pixels by 5 pixels, namely the first image segmentation result. The first convolution feature is a distinguishing feature that whether the first tooling position has product information or not can be detected more easily in the first image. Traversal refers to making one visit to each node in the tree (or graph) in turn along a search route. Through traversing and sequentially comparing the small areas with 5 x 5 pixels with the characteristics of the needle head of the injection needle in the processing process, the distinguishing characteristics between the first image and the second image only comprising the tooling equipment can be determined, the distinguishing characteristics are the traversing result of the first characteristics, and the traversing result provides a judgment reference for subsequently judging whether the tooling position image contains the injection needle product.

Step S800: judging whether the first product exists in the first image or not based on the first feature traversal result to obtain a first judgment result;

specifically, the first feature traversal result refers to a distinguishing feature between the first image and a second image only including the tooling equipment, and whether a plurality of 5 × 5 pixel regions obtained by dividing the first image are the same as the second image only including the tooling equipment can be obtained by performing information extraction and analysis on the first feature traversal result. If the first feature traversal result does not contain relevant information about the distinguishing feature, namely a first product, the first image and the second image are proved to be the same, and the first product is not contained, namely the injection needle product being processed is not contained; if the first feature traversal result contains the relevant information about the distinguishing feature, namely the first product, the first image is proved to be different from the second image, the first image contains the injection needle product being processed, and the second image only contains the tool position information. Therefore, whether the first product exists in the first image can be judged based on the first feature traversal result, and the judgment result is the first judgment result. Through the first judgment result, the first image can be divided into two types, one type contains the injection needle product being processed, and the other type does not contain the injection needle product being processed, so that subsequent counting is convenient to be carried out respectively.

Step S900: when the first judgment result is that the first image contains the first product, obtaining a first counting instruction;

step S1000: and counting the first products existing in the first tooling position through the first counting device according to the first counting instruction.

Specifically, the first counting device is a device capable of counting the number of pulses in real time, so as to realize the functions of measurement, counting and control. When the first determination result indicates that the first image includes the first product, that is, the first image has an obvious feature that the second image does not have, and the first feature traversal result includes related information about the first product, it indicates that the first image includes a needle product being processed, and the needle processing count prompt device issues a first count command. According to the first counting instruction, the first counting device counts the first tool bit. And counting the tool positions which are actually processed through the judgment result, and not counting the tool positions which are not actually processed, so that the counting result is ensured to accord with the actual situation.

Further, step S1100 in the embodiment of the present application includes:

step S1110: when the first judgment result is that the first image does not contain the first product, obtaining a first marking instruction;

step S1120: according to the first marking instruction, carrying out no-product marking on the first tool position;

step S1130: and when the intelligent counting device detects that the tool position without the product mark is carried out, the tool position is not subjected to product processing.

Specifically, when the first determination result indicates that the first product is not included in the first image, the device should not count the first tool position and issue a first marking instruction, and after receiving the first marking instruction, the counting prompt device for needle processing performs no-product marking on the first tool position. Because the first tool position does not contain the injection needle product being processed, when the intelligent counting device detects that the tool position without the product mark is carried out, the tool position is not subjected to product processing. The intelligent counting device is a module which can obtain a first judgment result in the counting prompting device for processing the injection needle. Through embedding in the counting assembly of syringe needle processing intelligent counting assembly can detect the frock position of discerning not carrying out the product processing, marks it when actual count, has guaranteed the accuracy of device processing count.

Further, step S1200 in the embodiment of the present application further includes:

step 1210: when the intelligent counting device detects that the tool position is a product mark, a first occupied product counting instruction is obtained;

step S1220: carrying out occupation counting on the first tooling position according to the first occupation product counting instruction;

step S1230: acquiring a first in-process product summarizing instruction, summarizing the quantity of all tool positions and products in an area to be processed according to the first in-process product summarizing instruction, and acquiring a first quantity summarizing result, wherein the first quantity summarizing result comprises the occupied product count;

step S1240: obtaining a first preset threshold value of the number of products to be processed;

step S1250: judging whether the first quantity summarizing result exceeds a first preset threshold value of the quantity of the products being processed;

step S1260: and when the first quantity summarizing result exceeds the first preset threshold value of the quantity of the products being processed, adjusting the quantity of the products in the area to be processed.

Particularly, when intelligent counting assembly detected that the frock position that has carried out no product marking, can not be right the frock position carries out product processing, nevertheless simultaneously can to the count suggestion device of syringe needle processing sends specific signal, the count suggestion device of syringe needle processing sends first occupy-place product count instruction promptly after receiving the signal. The first occupancy product counting instruction refers to the number of tool positions where no injection needle product is being processed.

Furthermore, the intelligent counting device sends a first product processing summary instruction, and the counting prompt device for the injection needle processing collects the number of all the tool positions and the products in the area to be processed after receiving the instruction, so that the summary result becomes a first number summary result. The first quantity summarizing result comprises the number of tool positions where the injection needle products are being processed, the number of tool positions where the injection needle products are not being processed and the number of products in a to-be-processed area.

The first preset threshold value of the number of the products to be processed refers to the maximum injection needle product quantity which can be processed simultaneously within the same time and is obtained by combining the number of the tool positions, the actual conditions of workers and the like according to the number of orders. And when the first quantity summarizing result exceeds the first preset threshold value of the quantity of the products to be processed, the counting prompt device for processing the injection needles sends prompt information, and the quantity of the products in the area to be processed is adjusted.

Through syringe needle processing counting assembly is processing frock position quantity in to production process, accounts for frock position quantity and treats the real-time record feedback of processing district quantity, and the personnel can be at any time treated the quantity of processing district product and adjust, have guaranteed going on in order of production and processing, have reached the technological effect of machining efficiency maximize.

Further, step S1300 in the embodiment of the present application includes:

step 1310: obtaining a first yield count instruction;

step S1320: summarizing all the tool positions and the actual product number of the area to be processed according to the first yield counting instruction to obtain a first actual number summarizing result;

step S1330: obtaining a first preset product single-piece quantity threshold;

step S1340: judging whether the first actual quantity summarizing result meets the first preset product single quantity threshold value or not;

step S1350: and when the first actual quantity summarizing result meets the first preset product single piece quantity threshold value, obtaining a first early warning instruction, and performing product quantity early warning on the area to be processed according to the first early warning instruction.

Specifically, in order to calculate the maximum number of the injection needle products which can be produced in the workshop, the injection needle processing counting prompting device sends out a first output counting instruction, after the instruction is received, the device calculates the number of the injection needles which are being processed on all the tool positions and the number of the injection needles in the area to be processed, and the sum of the two data is the first actual number summarizing result. The first preset product single-piece quantity threshold value refers to the maximum range of the actually processed injection needle product quantity obtained by the device comprehensive analysis of the injection needle processing counting prompting method, namely the range including the sum of the number of the injection needles being processed and the number of the injection needles in the area to be processed. And when the first actual quantity summarizing result meets the first preset product single piece quantity threshold value, obtaining a first early warning instruction, and according to the first early warning instruction, carrying out product quantity early warning on the to-be-processed area by a system. The device calculates the actual quantity in a gathering mode, the intellectualization of the processing counting of the injection needles is improved, the early warning instruction sent by the device can remind workers to adjust the quantity of products in a to-be-processed area at any time, and the technical effect of intelligent management production and processing is achieved.

Further, in the step S700 of the embodiment of the present application, the performing feature traversal on the first image segmentation result based on the first convolution feature to obtain a first feature traversal result includes:

step S710: obtaining a first region image, a second region image and an Nth region image based on the first image segmentation result, wherein N is a positive integer greater than 1;

step S720: performing feature convolution on the first region image and the second region image in the first image segmentation result until the Nth region image based on the first convolution feature to obtain a feature convolution value set;

step S730: obtaining the first feature traversal result based on the summarized convolution values in the feature convolution value set.

Specifically, the first image division command is issued by a count presentation device for needle processing when the first image is obtained. The first image may be subjected to image segmentation according to the first image segmentation instruction, and a plurality of segmented first image segments obtained by segmentation are the first image segmentation results. The first image segmentation parts can be named as a first region image, a second region image and an Nth region image respectively based on the plurality of first image segmentation parts, wherein N is a positive integer larger than 1.

And performing feature convolution on the first region image and the second region image in the first image segmentation result until the Nth region image based on the first convolution feature to obtain N feature convolution values, wherein all the feature convolution values form the feature convolution value set. And performing feature traversal on the N regional images based on the first convolution features to obtain N feature traversal results, wherein all the feature traversal results form the first feature traversal result. Through right a plurality of characteristic convolution values have been obtained to first image is cut apart, make based on the first characteristic traversal result that convolution value obtained in the characteristic convolution value set is more accurate, has improved the rate of accuracy that the device detected the occupy-place product, has further improved the technical effect of the rate of accuracy of syringe needle processing counting assembly count.

Further, the apparatus is further connected to a second image capturing apparatus in a communication manner, where step S1400 in this embodiment of the present application includes:

step S1410: obtaining a third image by the second image acquisition device;

step S1420: obtaining a second quantity summarizing result based on the third image, wherein the second quantity summarizing result is a summary of all tool positions including the occupied product count and the quantity of products in the area to be processed;

step S1430: quantity-verifying the first quantity-aggregated result based on the second quantity-aggregated result;

step S1440: adjusting the number of products in the area to be processed based on the number verification result.

Specifically, the device is also in communication connection with a second image acquisition device, which is similar to the first image acquisition device, is a device capable of acquiring images in real time, and may be a camera device or the like. The second image acquisition device can acquire images of all parts of the production workshop in multiple angles and multiple distances, namely the third image. And obtaining a second quantity summarizing result based on the third image, wherein the second quantity summarizing result is consistent with the category contained in the first quantity summarizing result, namely the second quantity summarizing result comprises the number of the tool positions where the injection needle products are processed, the number of the tool positions where no injection needle product is processed and the number of the products in the area to be processed. Further, quantity comparison and verification are carried out on the first quantity summarizing result based on the second quantity summarizing result, and the quantity of the products in the area to be processed is adjusted based on the quantity verification result. If the second quantity summarizing result is larger than the first quantity summarizing result, reducing the quantity of the products in the area to be processed; and if the second quantity summarizing result is smaller than the first quantity summarizing result, increasing the quantity of the products in the area to be processed. Through the image that second image acquisition device gathered, the device can calculate the frock position quantity, the occupation quantity and the district's product quantity of waiting to process of being processing again, obtains total product quantity result of gathering, compares this result with the result that obtains before and verifies, has reached the technological effect that improves device count result accuracy.

Further, in the step S500 of the embodiment of the present application, performing a distinctive feature extraction according to the second image and the first product feature, and obtaining a first convolution feature based on a distinctive feature extraction result, the method includes:

step S510: constructing a feature extraction model, wherein the feature extraction model is obtained by training a plurality of groups of training data, and each group of the plurality of groups of training data comprises the second image, the first product feature and identification information identifying a feature extraction result;

step S520: and inputting the second image and the first product characteristic into the characteristic extraction model to obtain the first convolution characteristic.

Specifically, the second image refers to an image of a tool position; the first product characteristic is the needle head characteristic of the processed injection needle and is obtained by analyzing the tool position and extracting the images of the area near the tool position. The feature extraction model is a neural network model, namely a neural network model in machine learning, reflects many basic features of human brain functions, and is a highly complex nonlinear power learning device. The method can continuously perform self-training learning according to training data, and utilizes a convolutional neural network model to perform feature extraction, wherein the convolutional neural network is a feedforward neural network which comprises convolution calculation and has a deep structure and is one of the representative algorithms of deep learning. Each group of data in the multiple groups of training data comprises the second image, the first product characteristics and identification information for identifying characteristic extraction results, the characteristic extraction model is continuously corrected by self, and when the output information of the characteristic extraction model reaches a preset accuracy rate/convergence state, the supervised learning process is ended. By carrying out data training on the feature extraction model, the feature extraction model can process input data more accurately, and then the output first convolution feature is more accurate, so that the technical effects of accurately obtaining data information and improving the intellectualization of an evaluation result are achieved.

To sum up, the counting prompt method based on the injection needle processing provided by the embodiment of the application has the following technical effects:

Example two

Based on the counting prompting method based on the injection needle processing in the previous embodiment, the same inventive concept is also provided, the invention further provides a counting prompting device based on the injection needle processing, please refer to fig. 2, and the device comprises:

the first obtaining unit 11 is configured to obtain a first image through the first image acquisition device, where the first image is an image including a first tooling position;

the second obtaining unit 12: the second obtaining unit 12 is configured to obtain information of a first product, where the first product is a product currently subjected to needle processing;

the third obtaining unit 13: the third obtaining unit 13 is configured to obtain a first feature extraction instruction, perform feature extraction on the first product according to the first feature extraction instruction, and obtain a first product feature;

the fourth obtaining unit 14: the fourth obtaining unit 14 is configured to obtain a second image through the first image acquisition device, where the second image includes an image of the first tooling position when there is no product;

the fifth obtaining unit 15: the fifth obtaining unit 15 is configured to perform difference feature extraction according to the second image and the first product feature, and obtain a first volume feature based on a difference feature extraction result;

the sixth obtaining unit 16: the sixth obtaining unit 16 is configured to obtain a first image segmentation instruction, perform image segmentation on the first image according to the first image segmentation instruction, and obtain a first image segmentation result;

the seventh obtaining unit 17: the seventh obtaining unit 17 is configured to perform feature traversal on the first image segmentation result based on the first convolution feature, so as to obtain a first feature traversal result;

the eighth obtaining unit 18: the eighth obtaining unit 18 is configured to determine whether the first product exists in the first image based on the first feature traversal result, so as to obtain a first determination result;

ninth obtaining unit 19: the ninth obtaining unit 19 is configured to obtain a first counting instruction when the first determination result indicates that the first image includes the first product;

first counting unit 20: the first counting unit 20 is configured to count, according to the first counting instruction, that the first product exists in the first tooling position through the first counting device.

Further, the apparatus further comprises:

a tenth obtaining unit: the tenth obtaining unit is configured to obtain a first marking instruction when the first determination result indicates that the first image does not include the first product;

a first marking unit: the first marking unit is used for marking the first tool position without a product according to the first marking instruction;

a first detection unit: the first detection unit is used for not processing the product on the tool position when the intelligent counting device detects the tool position without the product mark.

Further, the apparatus further comprises:

an eleventh obtaining unit: the eleventh obtaining unit is used for obtaining a first occupied product counting instruction when the tooling position detected by the intelligent counting device is a no-product mark;

a second counting unit: the second counting unit is used for carrying out occupation counting on the first tooling position according to the first occupation product counting instruction;

a twelfth obtaining unit: the twelfth obtaining unit is configured to obtain a first in-process product summarizing instruction, summarize the quantities of all the tooling positions and the products in the area to be processed according to the first in-process product summarizing instruction, and obtain a first quantity summarizing result, where the first quantity summarizing result includes the occupied product count;

a thirteenth obtaining unit: the thirteenth obtaining unit is used for obtaining a first preset threshold value of the number of the products being processed;

a first judgment unit: the first judging unit is used for judging whether the first quantity summarizing result exceeds the first preset threshold value of the quantity of the products being processed;

a first adjusting unit: the first adjusting unit is used for adjusting the number of the products in the area to be processed when the first number summarizing result exceeds the first preset threshold value of the number of the products being processed.

Further, the apparatus further comprises:

obtaining a first yield count instruction;

a fourteenth obtaining unit: the fourteenth obtaining unit is used for summarizing all the tooling positions and the actual product quantity of the area to be processed according to the first yield counting instruction to obtain a summarized result of a first actual quantity;

a fifteenth obtaining unit: the fifteenth obtaining unit is used for obtaining a first preset product unit quantity threshold value;

a second judgment unit: the second judging unit is used for judging whether the first actual quantity summarizing result meets the first preset product single-piece quantity threshold value or not;

a fifteenth obtaining unit: the fifteenth obtaining unit is configured to obtain a first early warning instruction when the first actual quantity summary result meets the first preset product single quantity threshold, and perform product quantity early warning on the to-be-processed area according to the first early warning instruction.

Further, the apparatus further comprises:

a sixteenth obtaining unit: the sixteenth obtaining unit is configured to obtain a first region image, a second region image, and an nth region image based on the first image segmentation result, where N is a positive integer greater than 1;

a seventeenth obtaining unit: the seventeenth obtaining unit is configured to perform feature convolution on the first region image and the second region image in the first image segmentation result until the nth region image is subjected to a feature convolution value, so as to obtain a feature convolution value set;

an eighteenth obtaining unit: the eighteenth obtaining unit is configured to obtain the first feature traversal result based on the summarized convolution values in the feature convolution value set.

Further, the apparatus further comprises:

a nineteenth obtaining unit: the nineteenth obtaining unit is used for obtaining a third image through the second image acquisition device;

a twentieth obtaining unit: the twentieth obtaining unit is configured to obtain a second quantity summarizing result based on the third image, where the second quantity summarizing result is a summary of all the tooling positions including the occupancy product count and the number of products in the area to be processed;

a first verification unit: the first verification unit is configured to perform quantity verification on the first quantity aggregation result based on the second quantity aggregation result;

a second adjusting unit: the second adjusting unit is used for adjusting the number of the products in the area to be processed based on the number verification result.

Further, the apparatus further comprises:

a first building unit: the first construction unit is used for constructing a feature extraction model, wherein the feature extraction model is obtained by training a plurality of groups of training data, and each group of the plurality of groups of training data comprises the second image, the first product feature and identification information identifying a feature extraction result;

a twenty-first obtaining unit: the twenty-first obtaining unit is configured to input the second image and the first product feature into the feature extraction model, and obtain the first convolution feature.

In the present specification, the embodiments are described in a progressive manner, and each embodiment focuses on the difference from the other embodiments, the aforementioned counting indication method based on needle processing in the first embodiment of fig. 1 and the specific example are also applicable to the counting indication device based on needle processing in the present embodiment, and through the foregoing detailed description of the counting indication method based on needle processing and the device based on needle processing, those skilled in the art can clearly know that the counting indication device based on needle processing in the present embodiment is based on needle processing, so for the brevity of the description, detailed description is not repeated here. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Exemplary electronic device

The electronic device of the embodiment of the present application is described below with reference to fig. 3.

Fig. 3 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.

Based on the inventive concept of a method for counting and prompting based on needle processing as in the previous embodiments, the present invention further provides a device for counting and prompting based on needle processing, which has a computer program stored thereon, and when the program is executed by a processor, the program realizes the steps of any one of the methods for counting and prompting based on needle processing as described above.

Where in fig. 3 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 305 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium.

The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.

The application provides a counting prompting method based on injection needle processing, which is applied to a counting prompting device based on injection needle processing, wherein the method comprises the following steps: obtaining a first image through the first image acquisition device, wherein the first image is an image comprising a first tooling position; obtaining information of a first product, wherein the first product is a product which is currently subjected to injection needle processing; obtaining a first feature extraction instruction, and performing product feature extraction on the first product according to the first feature extraction instruction to obtain a first product feature; obtaining a second image through the first image acquisition device, wherein the second image comprises an image of the first tooling position when no product exists; according to the second image and the first product characteristics, distinguishing characteristic extraction is carried out, and first volume characteristics are obtained based on a distinguishing characteristic extraction result; obtaining a first image segmentation instruction, and performing image segmentation on the first image according to the first image segmentation instruction to obtain a first image segmentation result; performing feature traversal on the first image segmentation result based on the first convolution feature to obtain a first feature traversal result; judging whether the first product exists in the first image or not based on the first feature traversal result to obtain a first judgment result; when the first judgment result is that the first image contains the first product, obtaining a first counting instruction; and counting the first products existing in the first tooling position through the first counting device according to the first counting instruction. The technical problem of exist among the prior art unable real-time supervision and make statistics of syringe needle actual processing quantity, lead to unable accurate assurance syringe needle production and processing progress is solved. The real-time monitoring syringe needle course of working, the actual processing quantity of accurate record syringe needle have been reached, have further improved the production and processing syringe needle efficiency of enterprise, hold the technical effect of syringe needle processing progress accurately.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, the present application may take the form of an entirely software embodiment, an entirely hardware embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application is in the form of a computer program product that may be embodied on one or more computer-usable storage media having computer-usable program code embodied therewith. And such computer-usable storage media include, but are not limited to: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk Memory, a Compact Disc Read-Only Memory (CD-ROM), and an optical Memory.

The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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 1 flow or flows and/or block 1 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 of FIG. 1 and/or block diagram block or blocks of FIG. 1.

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 1 flow or flows and/or block 1 block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.

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

Claims

1. A counting prompting method based on injection needle processing is applied to an intelligent counting device which is in communication connection with a first image acquisition device and a first counting device, and comprises the following steps:

obtaining a first image through the first image acquisition device, wherein the first image is an image comprising a first tooling position;

obtaining information of a first product, wherein the first product is a product which is currently subjected to injection needle processing;

obtaining a first feature extraction instruction, and performing product feature extraction on the first product according to the first feature extraction instruction to obtain a first product feature;

obtaining a second image through the first image acquisition device, wherein the second image comprises an image of the first tooling position when no product exists;

according to the second image and the first product characteristics, distinguishing characteristic extraction is carried out, and first volume characteristics are obtained based on a distinguishing characteristic extraction result;

obtaining a first image segmentation instruction, and performing image segmentation on the first image according to the first image segmentation instruction to obtain a first image segmentation result;

performing feature traversal on the first image segmentation result based on the first convolution feature to obtain a first feature traversal result;

judging whether the first product exists in the first image or not based on the first feature traversal result to obtain a first judgment result;

when the first judgment result is that the first image contains the first product, obtaining a first counting instruction;

and counting the first products existing in the first tooling position through the first counting device according to the first counting instruction.

2. The method of claim 1, further comprising:

when the first judgment result is that the first image does not contain the first product, obtaining a first marking instruction;

according to the first marking instruction, carrying out no-product marking on the first tool position;

and when the intelligent counting device detects that the tool position without the product mark is carried out, the tool position is not subjected to product processing.

3. The method of claim 2, wherein the method further comprises:

when the intelligent counting device detects that the tool position is a product mark, a first occupied product counting instruction is obtained;

carrying out occupation counting on the first tooling position according to the first occupation product counting instruction;

acquiring a first in-process product summarizing instruction, summarizing the quantity of all tool positions and products in an area to be processed according to the first in-process product summarizing instruction, and acquiring a first quantity summarizing result, wherein the first quantity summarizing result comprises the occupied product count;

obtaining a first preset threshold value of the number of products to be processed;

judging whether the first quantity summarizing result exceeds a first preset threshold value of the quantity of the products being processed;

and when the first quantity summarizing result exceeds the first preset threshold value of the quantity of the products being processed, adjusting the quantity of the products in the area to be processed.

4. The method of claim 3, wherein the method further comprises:

obtaining a first yield count instruction;

summarizing all the tool positions and the actual product number of the area to be processed according to the first yield counting instruction to obtain a first actual number summarizing result;

obtaining a first preset product single-piece quantity threshold;

judging whether the first actual quantity summarizing result meets the first preset product single quantity threshold value or not;

and when the first actual quantity summarizing result meets the first preset product single piece quantity threshold value, obtaining a first early warning instruction, and performing product quantity early warning on the area to be processed according to the first early warning instruction.

5. The method of claim 1, wherein said feature traversing the first image segmentation result based on the first convolution feature to obtain a first feature traversal result, further comprising:

obtaining a first region image, a second region image and an Nth region image based on the first image segmentation result, wherein N is a positive integer greater than 1;

performing feature convolution on the first region image and the second region image in the first image segmentation result until the Nth region image based on the first convolution feature to obtain a feature convolution value set;

obtaining the first feature traversal result based on the summarized convolution values in the feature convolution value set.

6. The method of claim 3, wherein the device is further communicatively coupled to a second image acquisition device, further comprising:

obtaining a third image by the second image acquisition device;

obtaining a second quantity summarizing result based on the third image, wherein the second quantity summarizing result is a summary of all tool positions including the occupied product count and the quantity of products in the area to be processed;

quantity-verifying the first quantity-aggregated result based on the second quantity-aggregated result;

adjusting the number of products in the area to be processed based on the number verification result.

7. The method of claim 1, wherein said performing a discriminating feature extraction based on said second image and said first product feature, obtaining a first convolution feature based on a discriminating feature extraction result, further comprises:

constructing a feature extraction model, wherein the feature extraction model is obtained by training a plurality of groups of training data, and each group of the plurality of groups of training data comprises the second image, the first product feature and identification information identifying a feature extraction result;

and inputting the second image and the first product characteristic into the characteristic extraction model to obtain the first convolution characteristic.

8. A count prompting device based on injection needle processing, wherein the device comprises:

a first obtaining unit: the first obtaining unit is used for obtaining a first image through a first image acquisition device, wherein the first image is an image comprising a first tooling position;

a second obtaining unit: the second obtaining unit is used for obtaining information of a first product, wherein the first product is a product which is currently processed by the injection needle;

a third obtaining unit: the third obtaining unit is used for obtaining a first feature extraction instruction, and performing feature extraction on the first product according to the first feature extraction instruction to obtain a first product feature;

a fourth obtaining unit: the fourth obtaining unit is used for obtaining a second image through the first image acquisition device, wherein the second image comprises an image of the first tooling position when no product exists;

a fifth obtaining unit: the fifth obtaining unit is used for performing distinguishing feature extraction according to the second image and the first product feature, and obtaining a first convolution feature based on a distinguishing feature extraction result;

a sixth obtaining unit: the sixth obtaining unit is configured to obtain a first image segmentation instruction, perform image segmentation on the first image according to the first image segmentation instruction, and obtain a first image segmentation result;

a seventh obtaining unit: the seventh obtaining unit is configured to perform feature traversal on the first image segmentation result based on the first convolution feature to obtain a first feature traversal result;

an eighth obtaining unit: the eighth obtaining unit is configured to determine whether the first product exists in the first image based on the first feature traversal result, and obtain a first determination result;

a ninth obtaining unit: the ninth obtaining unit is configured to obtain a first counting instruction when the first determination result indicates that the first image includes the first product;

a first counting unit: the first counting unit is used for counting the first products existing in the first tooling position through a first counting device according to the first counting instruction.

9. A count prompting device based on injection needle processing, comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the method according to any one of claims 1 to 7.