CN115497033A

CN115497033A - Article placement device control method, apparatus, device, medium, and program product

Info

Publication number: CN115497033A
Application number: CN202211175546.1A
Authority: CN
Inventors: 邓泽露; 程希来; 徐克勤; 郑博嘉
Original assignee: Duodian Life Chengdu Technology Co ltd
Current assignee: Duodian Life Chengdu Technology Co ltd
Priority date: 2022-09-26
Filing date: 2022-09-26
Publication date: 2022-12-20

Abstract

The embodiment of the disclosure discloses an article placement device control method, an article placement device control device, an article placement device, a medium and a program product. One embodiment of the method comprises: inputting the article display image into a general target detection model to obtain an image coordinate information set; determining an item image set; inputting each item image to a first item identification model; inputting each item image to a second item identification model; for each first item identification information, in response to determining that the probability value is greater than a first preset threshold value, determining an included item number as an item identification result; in response to determining that the probability value is less than or equal to a first preset threshold: selecting target second item identification information; determining the included item number as an item identification result in response to the included similarity being greater than a second preset threshold; and controlling the article placing equipment to execute new operation on the articles in response to the determination that the similarity is less than or equal to the second preset threshold. This embodiment improves the accuracy of article identification and article placement.

Description

Article placement device control method, apparatus, device, medium, and program product

Technical Field

Embodiments of the present disclosure relate to the field of computer technologies, and in particular, to a method, an apparatus, a device, a medium, and a program product for controlling an article placement device.

Background

With the development of computer technology and the establishment of intelligent warehousing systems, the automatic identification of articles can be realized. At present, when putting articles, the mode of generally adopting is: and identifying the articles through the unified image identification model so as to place the articles according to the identification result.

However, the inventor finds that when the above-mentioned manner is adopted to place the article, the following technical problems often exist:

firstly, the article is not identified by adopting various identification models, so that the accuracy of article identification is low, and the error rate of the article placing position is high.

Secondly, the image recognition model aiming at similar article recognition is not adopted to recognize the articles, so that the accuracy rate of similar article recognition is low, and the error rate of article placement positions is high.

And thirdly, the object is not identified by adopting an image identification model aiming at new object identification, so that the accuracy of new object identification is low, and the error rate of the object placement position is high.

The above information disclosed in this background section is only for enhancement of understanding of the background of the inventive concept and, therefore, it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art in this country.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure propose an article placement device control method, apparatus, electronic device, computer-readable medium, and program product to solve one or more of the technical problems mentioned in the background section above.

In a first aspect, some embodiments of the present disclosure provide a method of item placement device control, the method comprising: acquiring an article display image in which each article is displayed; inputting the article display image into a pre-trained general target detection model to obtain image coordinate information corresponding to each article as an image coordinate information set; determining an article image set according to the image coordinate information set; inputting each article image in the article image set to a first article identification model trained in advance to obtain a first article identification information set, wherein first article identification information in the first article identification information set corresponds to an article image in the article image set, and the first article identification information in the first article identification information set comprises an article number and a probability value corresponding to the article number; inputting each article image in the article image set to a pre-trained second article identification model to obtain a second article identification information set, wherein the second article identification information in the second article identification information set corresponds to the article image in the article image set, the second article identification information in the second article identification information set comprises an article number and a similarity corresponding to at least one target article image, and the at least one target article image corresponds to the article number; for each first item identification information in the first item identification information set, in response to determining that the probability value included in the first item identification information is greater than a first preset threshold value, determining an item number included in the first item identification information as an item identification result; for each first item identification information in the first item identification information set, in response to determining that a probability value included in the first item identification information is less than or equal to the first preset threshold, performing the following steps: determining the object image corresponding to the first object identification information as a target object image; selecting second item identification information corresponding to the target item image from the second item identification information set as target second item identification information; in response to the fact that the similarity included in the target second item identification information is larger than a second preset threshold value, determining the item number included in the target second item identification information as an item identification result; and in response to determining that the similarity included in the target second item identification information is smaller than or equal to the second preset threshold, controlling the associated item placement equipment to execute an item on-item new operation corresponding to a target item, wherein the target item is an item corresponding to an item number included in the target second item identification information.

In a second aspect, some embodiments of the present disclosure provide an article holding device control apparatus, the apparatus comprising: an acquisition unit configured to acquire an article display image in which each article is displayed; a first input unit configured to input the article display image to a general-purpose object detection model trained in advance, and obtain each piece of image coordinate information corresponding to each article as an image coordinate information set; a first determining unit configured to determine an item image set according to the image coordinate information set; a second input unit, configured to input each item image in the item image set to a first item identification model trained in advance, to obtain a first item identification information set, where first item identification information in the first item identification information set corresponds to an item image in the item image set, and the first item identification information in the first item identification information set includes an item number and a probability value corresponding to the item number; a third input unit, configured to input each item image in the item image set to a pre-trained second item identification model to obtain a second item identification information set, where the second item identification information in the second item identification information set corresponds to an item image in the item image set, the second item identification information in the second item identification information set includes an item number and a similarity corresponding to at least one target item image, and the at least one target item image corresponds to the item number; a second determining unit configured to determine, for each first item identification information in the first item identification information set, an item number included in the first item identification information as an item identification result in response to determining that a probability value included in the first item identification information is greater than a first preset threshold; an execution unit configured to, for each first item identification information in the first item identification information set, in response to determining that a probability value included in the first item identification information is less than or equal to the first preset threshold, execute the following steps: determining the object image corresponding to the first object identification information as a target object image; selecting second item identification information corresponding to the target item image from the second item identification information set as target second item identification information; in response to the fact that the similarity included in the target second item identification information is larger than a second preset threshold value, determining the item number included in the target second item identification information as an item identification result; and in response to determining that the similarity included in the target second item identification information is smaller than or equal to the second preset threshold, controlling the associated item placing equipment to execute a new operation on an item corresponding to the target item, wherein the target item is an item corresponding to the item number included in the target second item identification information.

In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device, on which one or more programs are stored, which when executed by one or more processors cause the one or more processors to implement the method described in any implementation of the first aspect.

In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium on which a computer program is stored, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect.

In a fifth aspect, some embodiments of the present disclosure provide a computer program product comprising a computer program that, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

The above embodiments of the present disclosure have the following advantages: by the article placement equipment control method of some embodiments of the present disclosure, the accuracy of article identification is improved, and the error rate of article placement positions is reduced. Specifically, the reasons why the accuracy of identifying the article is low and the error rate of the article placement position is high are that: the article is not identified by adopting various identification models, so that the accuracy rate of article identification is low, and the error rate of article placement positions is high. Based on this, the article placing apparatus control method of some embodiments of the present disclosure, first, an article display image is acquired. Wherein each article is displayed in the article display image. Thereby, an article display image including each article can be obtained. Then, the article display image is input to a general-purpose object detection model trained in advance, and image coordinate information corresponding to each article is obtained as an image coordinate information set. Thus, coordinate information characterizing the position of the image may be obtained and may be used to determine an image of the article. And then, determining an article image set according to the image coordinate information set. Thus, an article image of each article can be obtained. Next, each item image in the item image set is input to a first item identification model trained in advance, and a first item identification information set is obtained. Wherein the first item identification information in the first item identification information set corresponds to an item image in the item image set. The first item identification information in the first item identification information set includes an item number and a probability value corresponding to the item number. Thus, the identified item number and the probability value for determining whether the item to be identified is an existing item can be obtained. Then, each article image in the article image set is input to a second article identification model trained in advance, and a second article identification information set is obtained. And the second article identification information in the second article identification information set corresponds to the article image in the article image set. The second item identification information in the second item identification information set comprises an item number and a similarity corresponding to at least one target item image. The at least one target item image corresponds to the item number. Thus, the similarity between the identified item number and the item to be identified for determining whether or not the identified item is a new item can be obtained. Then, for each first item identification information in the first item identification information set, in response to determining that the probability value included in the first item identification information is greater than a first preset threshold value, determining the item number included in the first item identification information as an item identification result. Thus, when the probability value included in the first item identification information satisfies the determination condition of the probability value, the item number included in the first item identification information can be directly determined as the item identification result, and the item corresponding to the item identification result can represent the identified item. Next, for each first item identification information in the first item identification information set, in response to determining that a probability value included in the first item identification information is less than or equal to the first preset threshold, executing the following steps: first, an article image corresponding to the first article identification information is determined as a target article image. And a second step of selecting second item identification information corresponding to the target item image from the second item identification information set as target second item identification information. And thirdly, in response to the fact that the similarity included in the target second item identification information is larger than a second preset threshold value, determining the item number included in the target second item identification information as an item identification result. Thus, when the probability value included in the first item identification information does not satisfy the determination condition of the probability value, the similarity in the second item identification information can be further determined. Therefore, when the similarity satisfies the judgment condition of the similarity, the article number included in the target second article identification information can be determined as the article identification result. And the article corresponding to the article identification result can represent the identified article. And finally, controlling the associated article placing equipment to execute the new operation on the article corresponding to the target article in response to the fact that the similarity included in the target second article identification information is smaller than or equal to the second preset threshold. Wherein the target item is an item corresponding to the item number included in the target second item identification information. Thus, when the similarity does not satisfy the similarity determination condition, it can be determined that the target item does not exist, that is, the target item is a new item. So that the target item can be newly operated. Also, because of the article identification information identified by the first article identification model, an article satisfying the determination condition of the probability value can be identified. When the probability value does not satisfy the determination condition, an article satisfying the determination condition of the similarity may be identified based on the article identification information identified by the second article identification model. When the similarity does not meet the judgment condition, the article can be determined as a new article. Therefore, the accuracy rate of article identification is improved, and the error rate of article placement positions is reduced.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and components are not necessarily drawn to scale.

Fig. 1 is a flow chart of some embodiments of an article presentation device control method according to the present disclosure;

fig. 2 is a schematic structural view of some embodiments of an article presentation device control apparatus according to the present disclosure;

FIG. 3 is a schematic block diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 illustrates a flow 100 of some embodiments of an item placement device control method according to the present disclosure. The control method of the article placement equipment comprises the following steps:

step 101, an article display image is acquired.

In some embodiments, an executing subject (e.g., a computing device) of the item presentation device control method may acquire the item display image from the image capture device through a wired connection or a wireless connection. Wherein each article is displayed in the article display image. The article display image may be an image captured by the image capture device. The image acquisition device may be a device having a photographing function. For example, the image capturing devices described above may include, but are not limited to: cameras, computers and cell phones. It is noted that the wireless connection means may include, but is not limited to, a 3G/4G connection, a WiFi connection, a bluetooth connection, a WiMAX connection, a Zigbee connection, a UWB (ultra wideband) connection, and other wireless connection means now known or developed in the future.

Step 102, inputting the article display image into a general target detection model trained in advance, and obtaining each image coordinate information corresponding to each article as an image coordinate information set.

In some embodiments, the execution agent may input the article display image to a general-purpose object detection model trained in advance, and obtain the image coordinate information corresponding to each article. The general-purpose object detection model may be a neural network model that receives an article display image as an input and outputs image coordinate information corresponding to the article display image. For example, the neural network model may be a YOLO network (you only look once). The image coordinate information may be information representing the image coordinates of the article. Specifically, the image coordinate information may be (x, y, w, h). x may be the image center abscissa. y may be the image center ordinate. w may be the image length. h may be the image width. As an example, the image coordinate information may be (0.436262,0.474010,0.383663,0.178218).

And 103, determining an article image set according to the image coordinate information set.

In some embodiments, the execution subject may determine the set of item images from the set of image coordinate information.

In some optional implementations of some embodiments, for each image coordinate information in the set of image coordinate information, the executing subject may perform the following steps:

first, according to the image center coordinates included in the image coordinate information, the image position corresponding to the image coordinate information is determined. The image center coordinate may be a position of a center point of the image. The image center coordinates may represent a position of the article image corresponding to the image coordinate information. For example, the image center coordinates may be (0.436262,0.474010). In practice, the execution subject may determine the image center coordinates as an image position corresponding to the image coordinate information.

And secondly, determining the image size corresponding to the image coordinate information according to the image length and the image width included in the image coordinate information. The image size may represent a size of the article image corresponding to the image coordinate information. In practice, the execution subject may combine the image length and the image width into an image size corresponding to the image coordinate information. For example, the image size may be (0.383663,0.178218).

And thirdly, determining an article image corresponding to the image coordinate information according to the image position and the image size. The article image may be an image in which the image position corresponds to the image size. In practice, the executing body may cut out a rectangular image area of the image size from the center coordinates of the image as the object image.

And 104, inputting each article image in the article image set to a first article identification model trained in advance to obtain a first article identification information set.

In some embodiments, the executing subject may input each item image in the item image set to a first item identification model trained in advance, to obtain a first item identification information set. Wherein the first item identification information in the first item identification information set corresponds to an item image in the item image set. The first item identification information in the first item identification information set includes an item number and a probability value corresponding to the item number. The probability value may be a probability that the article corresponding to the article image to be recognized belongs to the article corresponding to the article number. The first article identification model may be a neural network model that takes an article image as an input and first article identification information corresponding to the article image as an output. For example, the neural network model may be a TransFG model (Transformer, self-attention model).

Optionally, the first item identification model may be trained by:

first, a first sample set is obtained. Wherein the first sample in the first sample set includes a first sample item image and first sample item identification information corresponding to the first sample item image. The first sample article identification information may be a sample label corresponding to the first sample article image. The first sample item identification information may include an item number and a probability value corresponding to the item number. The execution subject for training the first item identification model may be the execution subject, or may be another computing device.

A second step of performing the following first training step based on the first sample set:

and a first training step, namely respectively inputting the first sample article image of at least one first sample in the first sample set into the initial first article identification model to obtain first article identification information corresponding to each first sample in the at least one first sample. The initial first article identification model is an initial article identification model capable of obtaining first article identification information from an article image. The initial article identification model may be an article identification model to be trained.

And a second training step of comparing the first article identification information corresponding to each of the at least one first sample with the corresponding first sample article identification information. Wherein the comparison may be a comparison of the accuracy of the first article identification information corresponding to each of the at least one first sample and the corresponding first sample article identification information.

And a third training step, namely determining whether the initial first article identification model reaches a preset optimization target according to the comparison result. Here, the optimization objective may be that the loss function value of the initial first item identification model to be trained is smaller than a first preset threshold. Here, the loss function may be a cross entropy loss function. The first preset threshold may be 0.1.

A fourth training step of determining the initial first item identification model as a trained first item identification model in response to determining that the initial first item identification model achieves the optimization objective.

In some optional implementations of some embodiments, the step of training the first item identification model may further include:

and thirdly, in response to determining that the initial first article identification model does not meet the optimization goal, adjusting network parameters of the initial first article identification model, forming a first sample set by using unused first samples, using the adjusted initial first article identification model as the initial first article identification model, and executing the first training step again. As an example, the network parameters of the first item identification model may be adjusted by using a Back propagation Algorithm (BP Algorithm) and a gradient descent method (e.g., a small batch gradient descent Algorithm).

The first step to the third step and the related content thereof are taken as an invention point of the embodiment of the disclosure, and the technical problem mentioned in the background art is solved, namely, the problem that the image recognition model for similar article recognition is not adopted to recognize the article, so that the accuracy rate of similar article recognition is low, and further the error rate of the article placement position is high. The factors that lead to low accuracy in identifying similar articles and high error rate of placing articles are as follows: the image recognition model aiming at similar article recognition is not adopted to recognize the articles, so that the accuracy rate of similar article recognition is low, and the error rate of article placement positions is high. If the factors are solved, the effect of reducing the error rate of the placing positions of the articles can be achieved. To achieve this, first, a first set of samples is acquired. Wherein the first sample in the first sample set comprises a first sample item image and first sample item identification information corresponding to the first sample item image. Thus, data is obtained that can be used for training the initial first item identification model. Next, the following first training step is performed based on the first sample set: and respectively inputting the first sample article image of at least one first sample in the first sample set into the initial first article identification model to obtain first article identification information corresponding to each first sample in the at least one first sample. Comparing the first item identification information corresponding to each of the at least one first samples with the corresponding first sample item identification information. And determining whether the initial first article identification model reaches a preset optimization target or not according to the comparison result. In response to determining that the initial first item identification model achieves the optimization goal, the initial first item identification model is determined to be a trained first item identification model. Therefore, the training of the model is completed, whether the initial first article identification model reaches a preset optimization target or not can be determined according to the comparison result, and the initial first article identification model reaching the optimization target is determined as the first article identification model. The accuracy rate of similar article identification is improved. Finally, in response to determining that the initial first item identification model does not meet the optimization objective, network parameters of the initial first item identification model are adjusted, and the unused first samples are used to form a first sample set, and the adjusted initial first item identification model is used as the initial first item identification model, and the first training step is performed again. Therefore, because the initial first article identification model does not reach the optimization target, the network parameters of the initial first article identification model can be continuously adjusted and optimized, and the unused first samples are continuously used to form the first sample set for model training, so that the method can be used for generating a better similar article identification model. And based on the first sample set, the initial first article identification model can be trained continuously, and the network parameters of the initial first article identification model can be adjusted continuously. Therefore, the network parameters under the condition that the first article identification model has higher similar article identification accuracy are obtained, the accuracy of similar article identification is further improved, and the error rate of article placement positions is reduced.

And 105, inputting each article image in the article image set to a pre-trained second article identification model to obtain a second article identification information set.

In some embodiments, the executing subject may input each item image in the item image set to a second item identification model trained in advance, so as to obtain a second item identification information set. And the second article identification information in the second article identification information set corresponds to the article image in the article image set. The second item identification information in the second item identification information set comprises an item number and a similarity corresponding to at least one target item image. The at least one target item image corresponds to the item number. The item number corresponds to a target item image with the largest similarity in the at least one target item image. Here, the target item image may be an image of an item corresponding to the item number selected in advance. The article number may be a code symbol for distinguishing the target article from any other article. For example, the item number may be SKU 10111948B. The second item identification model may be a neural network model that takes an item image as an input and outputs second item identification information corresponding to the item image. For example, the Neural Network model may be a CNN Network (Convolutional Neural Network).

Optionally, the second article identification model is obtained by training in the following manner:

in a first step, a second sample set is obtained. Wherein the second sample in the second sample set includes a second sample item image and second sample item identification information corresponding to the second sample item image. The second sample article identification information may be a sample label corresponding to the second sample article image. The second sample item identification information may include an item number and a similarity corresponding to the at least one target item image. The execution subject for training the second article recognition model may be the execution subject, or may be another computing device.

A second step of performing, based on the second set of samples, a second training step of:

in the first substep, the second sample object images of at least one second sample in the second sample set are respectively input into the initial second object identification model, so as to obtain second object identification information corresponding to each second sample in the at least one second sample. The initial second article identification model is an initial article identification model capable of obtaining second article identification information according to the article image. The initial article identification model may be an article identification model to be trained.

And a second sub-step of comparing the second article identification information corresponding to each of the at least one second sample with the corresponding second sample article identification information. The comparison may be a comparison between the second item identification information corresponding to each of the at least one second sample and the accuracy of the corresponding second sample item identification information.

And a third substep of determining whether the initial second item identification model reaches a preset optimization target according to the comparison result. Here, the optimization objective may be that the loss function value of the initial second item identification model to be trained is smaller than a second preset threshold. Here, the loss function may be a comparative loss function. The second preset threshold may be 0.08.

And a fourth substep of determining the initial second item identification model as a trained second item identification model in response to determining that the initial second item identification model meets the optimization objective.

In some optional implementations of some embodiments, the step of training the second item identification model may further include:

and thirdly, in response to the fact that the initial second article identification model does not reach the optimization target, adjusting network parameters of the initial second article identification model, forming a second sample set by using unused second samples, using the adjusted initial second article identification model as the initial second article identification model, and executing the second training step again. The network parameters of the second item identification model may be adjusted by using a Back propagation Algorithm (BP Algorithm) and a gradient descent method (e.g., a small batch gradient descent Algorithm).

The first step to the third step and the related content thereof are taken as an invention point of the embodiment of the disclosure, and the technical problem mentioned in the background art is solved, namely, the problem that the image recognition model for recognizing the new product is not adopted to recognize the article, so that the accuracy rate of recognizing the new product is low, and further the error rate of the article placement position is high. Factors that lead to low accuracy in identifying new products and high error rate in placing articles are as follows: the method has the advantages that the object is not identified by the image identification model aiming at the new object identification, so that the accuracy of identifying the new object is low, and the error rate of the placing position of the object is high. If the factors are solved, the effect of reducing the error rate of the placing positions of the articles can be achieved. To achieve this, first, a second set of samples is taken. Wherein the second sample in the second sample set includes a second sample item image and second sample item identification information corresponding to the second sample item image. Thus, data is obtained that may be used for training the initial second item identification model. Secondly, the following second training step is performed based on the second set of samples: and respectively inputting the second sample article image of at least one second sample in the second sample set into the initial second article identification model to obtain second article identification information corresponding to each second sample in the at least one second sample. And comparing the second article identification information corresponding to each second sample in the at least one second sample with the corresponding second sample article identification information. And determining whether the initial second article identification model reaches a preset optimization target according to the comparison result. In response to determining that the initial second item identification model meets the optimization objective, determining the initial second item identification model as a trained second item identification model. Therefore, the training of the model is completed, whether the initial second article identification model reaches the preset optimization target or not can be determined according to the comparison result, the initial second article identification model reaching the optimization target is determined as the second article identification model, and the accuracy of new article identification is improved. And finally, in response to determining that the initial second item identification model does not meet the optimization goal, adjusting network parameters of the initial second item identification model, forming a second sample set by using unused second samples, using the adjusted initial second item identification model as the initial second item identification model, and executing the second training step again. Therefore, because the initial second article identification model does not reach the optimization target, the network parameters of the initial second article identification model can be continuously adjusted and optimized, and the unused second sample is continuously used to form a second sample set for model training, so that the method can be used for generating a more optimal new article identification model. And based on the second sample set, the initial second article identification model can be continuously trained, and the network parameters of the initial second article identification model are continuously adjusted and optimized, so that the network parameters of the second article identification model under the condition of high article identification accuracy are obtained, the accuracy of new article identification is improved, and the error rate of article placement positions is reduced.

And step 106, for each first item identification information in the first item identification information set, in response to determining that the probability value included in the first item identification information is greater than a first preset threshold value, determining the item number included in the first item identification information as an item identification result.

In some embodiments, for each first item identification information in the first item identification information set, in response to determining that the probability value included in the first item identification information is greater than a first preset threshold, the execution subject may determine an item number included in the first item identification information as an item identification result. The first preset threshold may be a preset probability value. For example, the first preset threshold may be 0.7.

In some optional implementations of some embodiments, the executing body may further perform the following steps:

first, an item number included in the first item identification information is determined as a first item number.

And secondly, determining the inventory quantity of the first item corresponding to the first item number according to the first item number. In practice, the executing entity may obtain, from a warehouse system terminal storing the inventory data, an article inventory quantity corresponding to the first article number as the first article inventory quantity. The inventory quantity of the article may be the remaining inventory quantity of the article. The warehouse system terminal may be a terminal that stores the inventory quantity of the first item.

And thirdly, controlling the associated sound playing equipment to play the first inventory prompt message in response to the fact that the inventory quantity of the first articles is larger than a third preset threshold value. The first inventory prompting message may be a message for prompting the executing entity to pay attention to the inventory quantity of the first item. For example, the first inventory guidance information may be "the remaining inventory amount of the item 001 is 150, the inventory is sufficient, and replenishment is not needed at all". The third preset threshold may be 100. The aforementioned "150" may be the first item inventory quantity. The "001" may be the item number. The sound reproducing apparatus may be an apparatus for reproducing sound. For example, the sound playing device may include, but is not limited to: power amplifier, audio amplifier, multimedia console and digital sound console.

And fourthly, controlling the sound playing equipment to play second inventory prompt information in response to the fact that the inventory quantity of the first articles is smaller than or equal to the third preset threshold value. The second inventory prompting message may be a message for prompting the executing body to pay attention to the inventory quantity of the first item and replenish the first item in time. For example, the second inventory guidance information may be "the remaining inventory amount of the item 002 is 30, the inventory is insufficient, and the user is required to pay attention to timely replenishment". The "30" may be the first item inventory quantity. The "002" may be the above article number.

Step 107, for each first item identification information in the first item identification information set, in response to determining that the probability value included in the first item identification information is less than or equal to a first preset threshold, performing the following steps:

at step 1071, the item image corresponding to the first item identification information is determined as the target item image.

Step 1072 selects second item identification information corresponding to the target item image from the set of second item identification information as the target second item identification information.

Step 1073, in response to determining that the similarity included in the target second item identification information is greater than the second preset threshold, determining the item number included in the target second item identification information as an item identification result.

In some embodiments, in response to determining that the similarity included in the target second item identification information is greater than a second preset threshold, the executing entity may determine the item number included in the target second item identification information as an item identification result. The second preset threshold may be a preset similarity. For example, the second preset threshold may be 0.75.

first, the item number included in the target second item identification information is determined as a second item number.

And secondly, determining the inventory quantity of the second item corresponding to the second item number according to the second item number. In practice, the executing entity may obtain, from a terminal of the warehouse system storing the inventory data, an inventory quantity of the item whose corresponding item number is the second item number as the second item inventory quantity. The inventory quantity of the items may be the remaining inventory quantity of the items. The warehouse system terminal may be a terminal for storing the inventory amount of the second item.

And thirdly, controlling the associated sound playing equipment to play third inventory prompt information in response to the fact that the quantity of the second inventory is larger than a fourth preset threshold value. The fourth preset threshold may be 60. The third inventory prompting message may be a message for prompting the executive body to pay attention to the article type and the inventory quantity of the article. The article type may be an article type representing a warehousing duration of the target article. For example, the above item types may include, but are not limited to: new products and similar items. The execution subject can determine the type of the article according to the magnitude relation between the probability value and the first preset threshold value. Specifically, the executing agent may determine, as a similar item, an item having a probability value greater than a first preset threshold corresponding to the item, and determine, as a new item, an item having a probability value less than or equal to the first preset threshold corresponding to the item. For example, the third stock prompting message may be "item 003 may be a new item, the remaining stock amount is 90, and please note that the sales amount is observed". The above "003" may be an article number. The "90" may be the second item inventory quantity.

And fourthly, controlling the sound playing equipment to play fourth inventory prompt information in response to the fact that the quantity of the second inventory is smaller than or equal to the fourth preset threshold value. The fourth inventory prompting message may be a message that prompts the executing entity to pay attention to the type and the sufficient inventory of the article. For example, the fourth inventory prompt message may be "item 004 may be a new item, the amount of remaining inventory is 30, and please pay attention to timely replenishment". Wherein the "004" may be an article number. The "30" may be the second item inventory quantity.

In response to determining that the similarity included in the target second item identification information is less than or equal to a second preset threshold, controlling the associated item placement device to perform an on-item new operation corresponding to the target item, step 1074.

In some embodiments, in response to determining that the similarity included in the target second item identification information is less than or equal to the second preset threshold, the executing entity may control the associated item placing device to execute the on-item new operation corresponding to the target item. Wherein the target item is an item corresponding to the item number included in the target second item identification information.

In practice, in response to determining that the similarity included in the target second item identification information is less than or equal to the second preset threshold, the executing body may control the associated item placing device to execute the new on-item operation corresponding to the target item by:

the first step is to acquire first article information corresponding to the target article. The first item information may be information corresponding to the target item. The first item information may include, but is not limited to: country code, producer code, item code, shelf number code, and check code. In practice, the executing entity may obtain the first item information corresponding to the target item from a terminal of the warehouse system storing the inventory data. The warehouse system terminal may be a terminal for storing first item information of the target item.

And a second step of generating item barcode information based on the first item information. The article barcode information may represent information that a target article may be put into and taken out of a warehouse. For example, the item barcode information may be 690 1234 56789 564 2. Where 690 may represent a country code. 1234 may represent a producer code. 56789 may represent an item code. 564 may represent a shelf number code. 2 may represent a check code. In practice, the executing agent may generate item barcode information corresponding to the first item information using barcode generator software. The barcode generator software may be generator software provided by any software vendor.

And a third step of determining the inventory quantity of the target item according to the item number of the target item. In practice, the executing entity may obtain the inventory quantity corresponding to the item number of the target item from the warehouse system terminal storing the inventory data.

And a fourth step of controlling the article placing device to execute new operation on the article corresponding to the target article according to the article bar code information and the inventory quantity. In practice, first, the execution body may determine a product of the stock quantity and a preset value as a candidate value. The preset value may be any value greater than 0 and less than 1. Then, the rounded value of the candidate value can be determined as the last new target item quantity. Here, the rounded value may be a value rounded up to the candidate value or may be a value rounded down to the candidate value. Next, the execution agent may determine a position indicated by a shelf number code included in the item barcode information as the placement position of the target item. Finally, the execution body can control the article placing device to place the target number of articles corresponding to the target articles to the determined placing positions. Here, the article placing device may be a device for placing an article. For example, the above-mentioned article holding device may include, but is not limited to: intelligent robotic arm, intelligent robot.

Optionally, for each target article corresponding to a new operation on the article, the executing body may further perform the following steps:

firstly, scanning the article bar code of the target article to obtain article bar code information. In practice, the executing agent may scan the item barcode of the target item by using a Radio Frequency Identification (RFID) technology to obtain item barcode information.

And secondly, scanning the shelf bar code corresponding to the target article on the shelf on which the target article is placed to obtain shelf bar code information. Here, the shelf barcode corresponding to the target item may be a barcode at a position where the target item is placed on the shelf. In practice, the executing body may scan shelf bar codes corresponding to the target item on a shelf on which the target item is placed by using a radio frequency identification technology, so as to obtain shelf bar code information.

And thirdly, in response to the fact that the article bar code information is matched with the goods shelf bar code information, controlling sound playing equipment to play article placement completion prompt information.

In practice, in response to determining that the article barcode information matches the shelf barcode information, the execution subject may control the sound playing device to play article placement completion prompt information. The article placement completion prompt information can be information for prompting completion of article placement. For example, the article placement completion prompt message may be "the article 006 has been placed. Here, the matching may be matching of the item barcode information and the shelf barcode information content. Specifically, the matching may be that the item barcode information is the same as a country code, a producer code, an item code, and a shelf number code included in the shelf barcode information.

The above embodiments of the present disclosure have the following advantages: by the article placement equipment control method of some embodiments of the present disclosure, the accuracy of article identification is improved, and the error rate of article placement positions is reduced. Specifically, the reasons why the accuracy of article identification is low and the error rate of article placement position is high are that: the article is not identified by adopting various identification models, so that the accuracy rate of article identification is low, and the error rate of article placement positions is high. Based on this, the article placing apparatus control method of some embodiments of the present disclosure, first, an article display image is acquired. Wherein each article is displayed in the article display image. Thereby, an article display image including each article can be obtained. Then, the article display image is input to a general-purpose object detection model trained in advance, and image coordinate information corresponding to each article is obtained as an image coordinate information set. Thus, coordinate information characterizing the position of the image may be obtained and may be used to determine an image of the article. And then, determining an article image set according to the image coordinate information set. This makes it possible to obtain an article image of each article. Next, each item image in the item image set is input to a first item identification model trained in advance, and a first item identification information set is obtained. Wherein the first item identification information in the first item identification information set corresponds to an item image in the item image set. The first item identification information in the first item identification information set includes an item number and a probability value corresponding to the item number. Thus, the identified item number and the probability value for determining whether the item to be identified is an existing item can be obtained. Then, each article image in the article image set is input to a second article identification model trained in advance, and a second article identification information set is obtained. And the second article identification information in the second article identification information set corresponds to the article image in the article image set. The second item identification information in the second item identification information set comprises an item number and a similarity corresponding to at least one target item image. The at least one target item image corresponds to the item number. Thus, the similarity between the identified item number and the item to be identified for determining whether or not the identified item is a new item can be obtained. Then, for each first item identification information in the first item identification information set, in response to determining that the probability value included in the first item identification information is greater than a first preset threshold value, determining the item number included in the first item identification information as an item identification result. Thus, when the probability value included in the first item identification information satisfies the determination condition of the probability value, the item number included in the first item identification information can be directly determined as the item identification result, and the item corresponding to the item identification result can represent the identified item. Next, for each first item identification information in the first item identification information set, in response to determining that a probability value included in the first item identification information is less than or equal to the first preset threshold, executing the following steps: first, an article image corresponding to the first article identification information is determined as a target article image. And a second step of selecting second item identification information corresponding to the target item image from the second item identification information set as target second item identification information. And thirdly, in response to the fact that the similarity included in the target second item identification information is larger than a second preset threshold value, determining the item number included in the target second item identification information as an item identification result. Thus, when the probability value included in the first item identification information does not satisfy the determination condition of the probability value, the similarity in the second item identification information can be further determined. Thus, when the similarity satisfies the determination condition of the similarity, the article number included in the target second article identification information can be determined as the article identification result. And the article corresponding to the article identification result can represent the identified article. And finally, controlling the associated article placing equipment to execute the new operation on the article corresponding to the target article in response to the fact that the similarity included in the target second article identification information is smaller than or equal to the second preset threshold. The target item is an item corresponding to the item number included in the target second item identification information. Thus, when the similarity does not satisfy the similarity determination condition, it can be determined that the target item does not exist, that is, the target item is a new item. So that the target item can be newly operated. Also, because of the article identification information identified by the first article identification model, an article satisfying the determination condition of the probability value can be identified. When the probability value does not satisfy the determination condition, an article satisfying the determination condition of the similarity may be identified based on the article identification information identified by the second article identification model. When the similarity does not satisfy the determination condition, the article can be determined as a new article. Therefore, the accuracy rate of article identification is improved, and the error rate of article placement positions is reduced.

With further reference to fig. 2, as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of an article placement device control apparatus, which correspond to those of the method embodiments shown in fig. 1, and which may be applied in various electronic devices in particular.

As shown in fig. 2, the article placement device control apparatus 200 of some embodiments includes: an acquisition unit 201, a first input unit 202, a first determination unit 203, a second input unit 204, a third input unit 205, a second determination unit 206, and an execution unit 207. Wherein the acquisition unit 201 is configured to acquire an item display image in which each item is displayed; the first input unit 202 is configured to input the article display image to a general-purpose object detection model trained in advance, to obtain each image coordinate information corresponding to each article as an image coordinate information set; the first determining unit 203 is configured to determine an item image set according to the image coordinate information set; the second input unit 204 is configured to input each item image in the item image set to a first item identification model trained in advance, so as to obtain a first item identification information set, wherein first item identification information in the first item identification information set corresponds to an item image in the item image set, and the first item identification information in the first item identification information set comprises an item number and a probability value corresponding to the item number; the third input unit 205 is configured to input each item image in the item image set to a second item identification model trained in advance, so as to obtain a second item identification information set, where the second item identification information in the second item identification information set corresponds to the item image in the item image set, the second item identification information in the second item identification information set includes an item number and a similarity corresponding to at least one target item image, and the at least one target item image corresponds to the item number; the second determining unit 206 is configured to, for each first item identification information in the first item identification information set, determine an item number included in the first item identification information as an item identification result in response to determining that a probability value included in the first item identification information is greater than a first preset threshold; the executing unit 207 is configured to, for each first item identification information in the first item identification information set, in response to determining that the probability value included in the first item identification information is less than or equal to the first preset threshold, execute the following steps: determining an article image corresponding to the first article identification information as a target article image; selecting second item identification information corresponding to the target item image from the second item identification information set as target second item identification information; in response to the fact that the similarity included in the target second item identification information is larger than a second preset threshold value, determining the item number included in the target second item identification information as an item identification result; and in response to determining that the similarity included in the target second item identification information is smaller than or equal to the second preset threshold, controlling the associated item placement equipment to execute an item on-item new operation corresponding to a target item, wherein the target item is an item corresponding to an item number included in the target second item identification information.

It is to be understood that the units described in the article presentation device control apparatus 200 correspond to the respective steps in the method described with reference to fig. 1. Thus, the operations, features and resulting advantages described above with respect to the method are also applicable to the apparatus 200 and the units included therein, and are not described herein again.

Referring now to FIG. 3, a block diagram of an electronic device 300 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 3, electronic device 300 may include a processing apparatus (e.g., computing device) 301 that may perform various suitable actions and processes in accordance with programs stored in a Read Only Memory (ROM) 302 or loaded from a storage 308 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data necessary for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.

Generally, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, or the like; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage devices 308 including, for example, magnetic tape, hard disk, etc.; and a communication device 309. The communication means 309 may allow the electronic device 300 to communicate with other devices, wireless or wired, to exchange data. While fig. 3 illustrates an electronic device 300 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 3 may represent one device or may represent multiple devices, as desired.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. The computer program, when executed by the processing apparatus 301, performs the above-described functions defined in the methods of some embodiments of the present disclosure.

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

In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (Hyper Text Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring an article display image in which each article is displayed; inputting the article display image into a pre-trained general target detection model to obtain image coordinate information corresponding to each article as an image coordinate information set; determining an article image set according to the image coordinate information set; inputting each article image in the article image set to a first article identification model trained in advance to obtain a first article identification information set, wherein first article identification information in the first article identification information set corresponds to an article image in the article image set, and the first article identification information in the first article identification information set comprises an article number and a probability value corresponding to the article number; inputting each article image in the article image set to a pre-trained second article identification model to obtain a second article identification information set, wherein the second article identification information in the second article identification information set corresponds to the article image in the article image set, the second article identification information in the second article identification information set comprises an article number and a similarity corresponding to at least one target article image, and the at least one target article image corresponds to the article number; for each first item identification information in the first item identification information set, in response to determining that the probability value included in the first item identification information is greater than a first preset threshold value, determining an item number included in the first item identification information as an item identification result; for each first item identification information in the first item identification information set, in response to determining that a probability value included in the first item identification information is less than or equal to the first preset threshold, performing the following steps: determining the object image corresponding to the first object identification information as a target object image; selecting second item identification information corresponding to the target item image from the second item identification information set as target second item identification information; in response to the fact that the similarity included in the target second item identification information is larger than a second preset threshold value, determining the item number included in the target second item identification information as an item identification result; and in response to determining that the similarity included in the target second item identification information is smaller than or equal to the second preset threshold, controlling the associated item placement equipment to execute an item on-item new operation corresponding to a target item, wherein the target item is an item corresponding to an item number included in the target second item identification information.

Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

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

The units described in some embodiments of the present disclosure may be implemented by software, and may also be implemented by hardware. The described units may also be provided in a processor, and may be described as: a processor includes an acquisition unit, a first input unit, a first determination unit, a second input unit, a third input unit, a second determination unit, and an execution unit. Where the names of these units do not in some cases constitute a limitation on the unit itself, for example, the capture unit may also be described as a "unit that captures an image of the article display".

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), complex Programmable Logic Devices (CPLDs), and the like.

Some embodiments of the present disclosure also provide a computer program product comprising a computer program which, when executed by a processor, implements any of the above-described article presentation device control methods.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combinations of the above-mentioned features, and other embodiments in which the above-mentioned features or their equivalents are combined arbitrarily without departing from the spirit of the invention are also encompassed. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.

Claims

1. An article placement device control method comprising:

acquiring an item display image, wherein each item is displayed in the item display image;

inputting the article display images into a pre-trained universal target detection model to obtain image coordinate information corresponding to each article as an image coordinate information set;

determining an article image set according to the image coordinate information set;

inputting each article image in the article image set to a pre-trained first article identification model to obtain a first article identification information set, wherein first article identification information in the first article identification information set corresponds to an article image in the article image set, and the first article identification information in the first article identification information set comprises an article number and a probability value corresponding to the article number;

inputting each article image in the article image set to a pre-trained second article identification model to obtain a second article identification information set, wherein the second article identification information in the second article identification information set corresponds to the article image in the article image set, the second article identification information in the second article identification information set comprises an article number and a similarity corresponding to at least one target article image, and the at least one target article image corresponds to the article number;

for each first item identification information in the first item identification information set, in response to determining that the probability value included by the first item identification information is greater than a first preset threshold value, determining an item number included by the first item identification information as an item identification result;

for each first item identification information in the first set of item identification information, in response to determining that the first item identification information includes a probability value that is less than or equal to the first preset threshold, performing the following steps:

determining an article image corresponding to the first article identification information as a target article image;

selecting second item identification information corresponding to the target item image from the second item identification information set as target second item identification information;

in response to the fact that the similarity included in the target second item identification information is larger than a second preset threshold value, determining the item number included in the target second item identification information as an item identification result;

and in response to the fact that the similarity included in the target second item identification information is smaller than or equal to the second preset threshold, controlling the associated item placing equipment to execute an item on-item new operation corresponding to a target item, wherein the target item is an item corresponding to an item number included in the target second item identification information.

2. The method of claim 1, wherein the image coordinate information in the set of image coordinate information comprises: image center coordinates, image length and image width; and

determining an article image set according to the image coordinate information set, including:

for each image coordinate information of the set of image coordinate information, performing the steps of:

determining an image position corresponding to the image coordinate information according to the image center coordinate included in the image coordinate information;

determining an image size corresponding to the image coordinate information according to the image length and the image width included in the image coordinate information;

and determining an article image corresponding to the image coordinate information according to the image position and the image size.

3. The method of claim 1, wherein the controlling, in response to determining that the degree of similarity included in the target second item identification information is less than or equal to the second preset threshold, the associated item placement device to perform an on-item new operation for the corresponding target item comprises:

acquiring first article information corresponding to the target article;

generating item barcode information based on the first item information;

determining the inventory quantity of the target item according to the item number of the target item;

and controlling the article placing equipment to execute new operation on the article corresponding to the target article according to the article bar code information and the inventory quantity.

4. The method of claim 3, wherein prior to said controlling the item placement device to perform the on-item new operation corresponding to the target item, the method further comprises:

for each target article corresponding to the new operation on the article, performing the following steps:

scanning the article bar code of the target article to obtain article bar code information;

scanning shelf bar codes corresponding to the target articles on a shelf for placing the target articles to obtain shelf bar code information;

and controlling sound playing equipment to play item placement completion prompt information in response to the fact that the item bar code information is matched with the shelf bar code information.

5. The method of claim 1, wherein after determining the item number included in the first item identification information as an item identification result in response to determining that the probability value included in the first item identification information is greater than a first preset threshold, the method further comprises:

determining the item number included in the first item identification information as a first item number;

determining the inventory quantity of a first item corresponding to the first item number according to the first item number;

in response to determining that the inventory quantity of the first item is greater than a third preset threshold, controlling an associated sound playing device to play first inventory prompt information;

and controlling the sound playing device to play second inventory prompt information in response to the fact that the inventory quantity of the first article is smaller than or equal to the third preset threshold value.

6. The method according to claim 1, wherein after determining that the item number included in the target second item identification information is an item identification result in response to determining that the degree of similarity included in the target second item identification information is greater than a second preset threshold, the method further comprises:

determining the article number included in the target second article identification information as a second article number;

determining the inventory quantity of the second item corresponding to the second item number according to the second item number;

in response to determining that the second item inventory quantity is greater than a fourth preset threshold, controlling an associated sound playing device to play third inventory prompt information;

and controlling the sound playing device to play fourth inventory prompt information in response to the fact that the inventory quantity of the articles is smaller than or equal to the fourth preset threshold value.

7. An article placing device control apparatus comprising:

an acquisition unit configured to acquire an article display image in which each article is displayed;

a first input unit configured to input the article display image to a general target detection model trained in advance, to obtain respective image coordinate information corresponding to the respective articles as an image coordinate information set;

a first determining unit configured to determine an item image set according to the image coordinate information set;

the second input unit is configured to input each item image in the item image set to a first item identification model trained in advance to obtain a first item identification information set, wherein first item identification information in the first item identification information set corresponds to an item image in the item image set, and the first item identification information in the first item identification information set comprises an item number and a probability value corresponding to the item number;

a third input unit, configured to input each item image in the item image set to a pre-trained second item identification model to obtain a second item identification information set, where the second item identification information in the second item identification information set corresponds to an item image in the item image set, the second item identification information in the second item identification information set includes an item number and a similarity corresponding to at least one target item image, and the at least one target item image corresponds to the item number;

a second determination unit configured to determine, for each first item identification information in the first item identification information set, an item number included in the first item identification information as an item identification result in response to determining that a probability value included in the first item identification information is greater than a first preset threshold;

an execution unit configured to, for each first item identification information in the first set of item identification information, in response to determining that a probability value included in the first item identification information is less than or equal to the first preset threshold, execute the following steps: determining an article image corresponding to the first article identification information as a target article image; selecting second item identification information corresponding to the target item image from the second item identification information set as target second item identification information; in response to the fact that the similarity included in the target second article identification information is larger than a second preset threshold value, determining an article number included in the target second article identification information as an article identification result; and in response to the fact that the similarity included in the target second item identification information is smaller than or equal to the second preset threshold, controlling the associated item placing equipment to execute a new operation on the item corresponding to the target item, wherein the target item is the item corresponding to the item number included in the target second item identification information.

8. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon;

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-6.

9. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1-6.

10. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1-6.