Product information acquisition method and device, computer equipment and storage medium

Abstract

The invention relates to a product information collection method and device, computer equipment and a storage medium. When an information acquisition instruction is detected, an acquisition rule is determined based on a product type needing to be acquired, and corresponding guidance information is output based on a target relative position and a target relative size in the acquisition rule through an acquisition model, so that acquisition personnel adjust the relative position and size of a product to be acquired in an acquisition page; and when the to-be-collected product in the collection page meets the target relative position and size, collecting product information. Compared with a traditional mode of collecting product information through manual training, guiding and the like, according to the scheme, the preset collection rule and the collection model are combined, the position and size guiding information of the product is output in real time in the collection process of collection personnel, and the product information is collected when the product conforms to the target position and size; therefore, the product information acquisition efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of neural network technology, and in particular, to a product information collection method, apparatus, computer device, storage medium, and computer program product. Background Art

[0002] With the development of the logistics industry, it has now become mainstream to transport products through logistics. Among them, there are numerous products transported through logistics, and a series of different types of products are stored on the shelves in each store of the logistics service. In order to perform data analysis on the products stored in each store, it is necessary to collect product information. Currently, the method of collecting product information is usually through manual training and guidance, etc. However, collecting product information through manual training and guidance, etc. will lead to a decrease in the efficiency of product information collection.

[0003] Therefore, the current product information collection method has the defect of low collection efficiency. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a product information collection method, apparatus, computer device, computer-readable storage medium, and computer program product that can improve the information collection efficiency.

[0005] In a first aspect, this application provides a product information collection method, and the method includes:

[0006] In response to an information collection instruction, display a collection page and obtain the product type of the product to be collected;

[0007] Obtain a preset collection rule corresponding to the product type; the preset collection rule includes the target relative position and target relative size of the product to be collected on the collection page;

[0008] Input the preset collection rule and the collection page into a trained collection model, and the collection model identifies the product area corresponding to the product to be collected on the collection page. According to the product area, the target relative position, and the target relative size, output corresponding guidance information; the guidance information is used to instruct the collector to adjust the relative position and relative size of the product area on the collection page;

[0009] When the product area meets the target relative position and target relative size, collect the product information of the product to be collected in the product area.

[0010] In one of the embodiments, the obtaining the preset collection rule corresponding to the product type includes:

[0011] Obtain the target product area position in the collection page preset for the product type, as well as the target product area distribution ratio in the collection page, and obtain the target relative position according to the target product area position and the target product area distribution ratio;

[0012] Obtain the target product area size in the collection page preset for the product type, and determine the target relative size according to the target product area size;

[0013] According to the target relative position and the target relative size, obtain the preset collection rule corresponding to the product type.

[0014] In one embodiment, the inputting the preset collection rule and the collection page into the trained collection model includes:

[0015] Input the preset collection rule and the collection page into the trained collection model, and the collection model identifies the product area corresponding to the product to be collected in the collection page;

[0016] According to the relative position of the product area in the collection page, output corresponding position guidance information; the position guidance information is used to instruct the collector to adjust the relative position of the product area in the collection page;

[0017] According to the relative size of the product area in the collection page, output corresponding size guidance information; the size guidance information is used to instruct the collector to adjust the relative size of the product area in the collection page.

[0018] In one embodiment, the outputting corresponding position guidance information according to the relative position of the product area in the collection page includes:

[0019] Obtain the preset collection area in the collection page;

[0020] According to the position of the product area in the collection area and the distribution ratio of the product area in the collection area, output corresponding position guidance information;

[0021] The position guidance information is used to instruct the collector to adjust the collection angle so that the product area is within the collection area and the distribution ratio of the product area to the collection area meets the preset distribution ratio.

[0022] In one embodiment, the outputting corresponding size guidance information according to the relative size of the product area in the collection page includes:

[0023] Obtain the page size of the acquisition page and the area size of the product area in the acquisition page;

[0024] Output corresponding size guidance information according to the area size;

[0025] The size guidance information is used to instruct the acquirer to adjust the acquisition distance so that the ratio of the area size to the page size meets a preset ratio.

[0026] In one embodiment, the preset acquisition rule further includes the display position corresponding to the product type; the inputting the preset acquisition rule and the acquisition page into the trained acquisition model includes:

[0027] Input the preset acquisition rule and the acquisition page into the trained acquisition model, and the acquisition model outputs corresponding acquisition angle guidance information according to the display position; the acquisition angle guidance information is used to instruct the acquirer to adjust the acquisition angle so that the product area of the product to be acquired in the acquisition page meets a preset display angle.

[0028] In one embodiment, the acquiring the product information of the product to be acquired in the product area when the product area meets the target relative position and the target relative size includes:

[0029] When the product area meets the target relative position and the target relative size, detect the product coordinates of the product to be acquired in the acquisition page according to the product area;

[0030] Determine the product information of the product to be acquired according to the product coordinates.

[0031] In a second aspect, the present application provides a product information acquisition device, and the device includes:

[0032] A response module, configured to respond to an information acquisition instruction, display an acquisition page, and obtain the product type of the product to be acquired;

[0033] An acquisition module, configured to acquire the preset acquisition rule corresponding to the product type; the preset acquisition rule includes the target relative position and the target relative size of the product to be acquired in the acquisition page;

[0034] A guidance module, configured to input the preset acquisition rule and the acquisition page into a trained acquisition model, and the acquisition model identifies the product area corresponding to the product to be acquired in the acquisition page, and outputs corresponding guidance information according to the product area, the target relative position, and the target relative size; the guidance information is used to instruct the acquirer to adjust the relative position and the relative size of the product area in the acquisition page;

[0035] An acquisition module, configured to acquire product information of a product to be acquired in the product area when the product area meets the target relative position and the target relative size.

[0036] In a third aspect, the present application provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the above method are implemented.

[0037] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0038] In a fifth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0039] For the above product information acquisition method, device, computer device, storage medium, and computer program product, when an information acquisition instruction is detected, an acquisition rule is determined based on the type of product to be acquired, and corresponding guidance information is output by an acquisition model based on the target relative position and the target relative size in the acquisition rule, so that the acquirer adjusts the relative position and size of the product to be acquired on the acquisition page, and when the product to be acquired on the acquisition page meets the target relative position and size, the product information is acquired. Compared with the traditional method of acquiring product information through manual training and guidance, etc., this solution combines a preset acquisition rule and an acquisition model to output real-time guidance information on the position and size of the product during the acquisition process by the acquirer, and acquires the product information when the product meets the target position and size, thereby improving the efficiency of product information acquisition. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic flowchart of a product information acquisition method in an embodiment;

[0041] Figure 2 It is a schematic interface diagram of product information acquisition steps in an embodiment;

[0042] Figure 3 It is a schematic interface diagram of a guidance information output step in an embodiment;

[0043] Figure 4 It is a schematic interface diagram of a guidance information output step in another embodiment;

[0044] Figure 5 It is a schematic interface diagram of a guidance information output step in yet another embodiment;

[0045] Figure 6Schematic diagram of the interface for the guiding information output step in yet another embodiment;

[0046] Figure 7 Structural block diagram of the product information acquisition device in one embodiment;

[0047] Figure 8 Internal structure diagram of a computer device in one embodiment. Detailed implementation manners

[0048] In order to make the objectives, technical solutions, and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0049] In one embodiment, as Figure 1 shown, a product information acquisition method is provided. In this embodiment, an example is given where this method is applied to a terminal. It can be understood that this method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server, including the following steps:

[0050] Step S202, in response to an information acquisition instruction, display an acquisition page and obtain the product type of the product to be acquired.

[0051] Among them, the acquisition personnel can use the terminal to acquire information about the product. Among them, the above terminal can be a handheld terminal, such as a mobile phone, etc. An image acquisition device is provided in the terminal, so that the image of the product's location scene can be acquired in real time, such as the images in scenarios such as logistics stores and offline stores. The acquisition personnel can trigger the corresponding information acquisition instruction in the above terminal, such as clicking the acquisition button or triggering it through a voice instruction. In response to the information acquisition instruction, the terminal can obtain the product type of the product to be acquired and display the acquisition page. Among them, the acquisition page can be an image acquisition page. In the acquisition page, the acquisition personnel can select to acquire the product information in the form of taking pictures or video recording.

[0052] Among them, the product type of the above product to be acquired can be determined based on the above information acquisition instruction. For example, the information acquisition instruction carries the product type of the product to be acquired. Specifically, the acquisition personnel can select the identifier of the product that needs to be acquired for information acquisition on the product selection page of the terminal. Then, the terminal determines the corresponding product type based on the selected product identifier. Thus, when detecting the trigger information of the information acquisition instruction by the acquisition personnel, an information acquisition instruction carrying the product type can be generated.

[0053] Step S204: Obtain the preset acquisition rules corresponding to the product type; the preset acquisition rules include the target relative position and target relative size of the product to be acquired on the acquisition page.

[0054] Among them, for different types of products in the logistics store, the terminal can use different preset acquisition rules for information acquisition. Then the terminal can pre-set different acquisition rules for different types of products in advance. Among them, the preset acquisition rules of the product can include the target relative position and target relative size of the product to be acquired on the acquisition page. Among them, the target relative position can be the expected position preset for the product to be acquired on the acquisition page, and the target relative size can be the expected size preset for the product to be acquired on the acquisition page. When the product to be acquired meets the above target relative position and target relative size, the terminal can acquire the relevant information of this type of product more comprehensively and effectively.

[0055] In addition, in some embodiments, the above preset acquisition rules further include the display position of the product. For different types of products, there can be corresponding display positions, and for products in different display positions, the terminal can also determine corresponding acquisition rules, such as the acquisition angle, etc.

[0056] Specifically, the above product types can include but are not limited to types such as daily chemicals, alcoholic beverages, beverages, milk powder, grain and oil, etc., and different types of products can correspond to different acquisition rules such as display positions, acquisition modes, target relative positions, and target relative sizes. Among them, the acquisition model can include modes such as taking pictures and videos, that is, acquiring the information of the above products by taking pictures or videos.

[0057] Step S206: Input the preset acquisition rules and the acquisition page into the trained acquisition model. The acquisition model identifies the product area corresponding to the product to be acquired on the acquisition page, and outputs corresponding guidance information according to the product area, the target relative position, and the target relative size; the guidance information is used to instruct the acquisition personnel to adjust the relative position and relative size of the product area on the acquisition page.

[0058] Among them, the terminal can pre-train the to-be-trained acquisition model by using the acquisition page samples, acquisition rule samples, and corresponding guidance information samples, and obtain the trained acquisition model. For example, the terminal inputs the acquisition page samples and acquisition rule samples into the to-be-trained acquisition model. The acquisition model detects the relative position and relative size of the product sample area in the acquisition page with respect to the acquisition page based on the above acquisition rule samples, and thus outputs the corresponding guidance information. The terminal can adjust the model parameters of the above acquisition model according to the matching degree between the guidance information output by the above acquisition model and the corresponding guidance information samples until the preset training end condition is met, and then obtain the trained acquisition model. Among them, the preset training end condition can include that within the preset number of training times, the above matching degree is greater than or equal to the preset matching degree threshold, or the above number of training times reaches the preset number of training times threshold. Among them, after the above acquisition model is trained, the terminal can package it into an SDK (Software Development Kit) and integrate it into the acquisition application in the terminal. Thus, the terminal can use the acquisition application combined with the above acquisition model to collect product information. Specifically, the above acquisition model can be a convolutional neural network model.

[0059] The terminal can input the above acquisition page and the preset acquisition rules into the trained acquisition model. The acquisition model identifies the product area corresponding to the product to be collected in the acquisition page, and based on the target relative position and target relative size in the preset acquisition rules, combines the relative position and relative size of the product area in the above acquisition page, and outputs the corresponding guidance information. Thus, the acquisition personnel can adjust the acquisition position of the terminal or the acquisition angle of the terminal according to the above guidance information, so that the product area in the acquisition page meets the above relative position and relative size. Among them, the above guidance information can be various. For example, it can be to display the corresponding prompt information on the acquisition page to prompt the acquisition personnel to move or adjust the shooting angle of the terminal; it can also be to output the corresponding voice prompt to prompt the acquisition personnel to move or adjust the shooting angle of the terminal, etc.

[0060] In addition, in some embodiments, the above preset acquisition rules further include the display positions corresponding to the product types. Different display positions can be displayed at different angles on the acquisition page, so that the terminal can more comprehensively and effectively acquire all the products displayed at the display positions. Then, the terminal can input the preset acquisition rules and the acquisition page into the trained acquisition model, and the acquisition model outputs the corresponding acquisition angle guidance information according to the display position. Thus, the acquisition personnel can adjust the acquisition angle of the terminal based on the acquisition angle guidance information, including by moving or adjusting the handheld angle of the terminal, etc., so that the product area of the product to be acquired on the acquisition page meets the preset display angle. For example, for display positions such as a display stack, the terminal can guide the acquisition personnel through the acquisition model to display the product area at a 45° angle on the acquisition page, so that two adjacent faces of the display stack can be completely photographed; for display positions such as a shelf, the terminal can guide the acquisition personnel through the acquisition model to display the product area vertically and with adjacent sides at a 90° angle on the acquisition page to completely acquire the information of each product on the shelf.

[0061] Step S208, when the product area meets the target relative position and the target relative size, acquire the product information of the product to be acquired in the product area.

[0062] Among them, the terminal can use the acquisition model to guide the acquisition personnel to adjust the position or the acquisition angle, so that the product area of the product to be acquired on the acquisition page meets the above target relative position and the target relative size. When the above product area meets the above target relative position and the target relative size, the terminal can acquire the product information of the product to be acquired based on the above product area. For example, in one embodiment, when the terminal determines that the product area meets the target relative position and the target relative size, the terminal can detect the product coordinates of the product to be acquired in the acquisition page according to the product area. And according to the product coordinates, determine the product information of the product to be acquired. Specifically, the terminal can directly use the above product coordinates as the product information. In some embodiments, the terminal can also obtain the product image of the product to be acquired based on the above product coordinates, and then obtain the product information of the product to be acquired by recognizing the product image.

[0063] In the above product information collection method, when an information collection instruction is detected, a collection rule is determined based on the product type to be collected. The collection model outputs corresponding guidance information based on the target relative position and target relative size in the collection rule, enabling the collection personnel to adjust the relative position and size of the product to be collected on the collection page. When the product to be collected on the collection page meets the target relative position and size, the product information is collected. Compared with the traditional method of collecting product information through manual training and guidance, etc., this solution combines a preset collection rule and a collection model to output real-time guidance information on the position and size of the product during the collection process by the collection personnel, and collects the product information when the product meets the target position and size, thereby improving the efficiency of product information collection.

[0064] In one embodiment, obtaining the preset collection rule corresponding to the product type includes: obtaining the target product area position in the collection page preset for the product type, and the target product area distribution ratio in the collection page, and obtaining the target relative position according to the target product area position and the target product area distribution ratio; obtaining the target product area size in the collection page preset for the product type, and determining the target relative size according to the target product area size; and obtaining the preset collection rule corresponding to the product type according to the target relative position and the target relative size.

[0065] In this embodiment, the terminal can use multiple judgment conditions to construct the collection rule for each product type. For example, for the target relative position, the terminal can obtain the target product area position in the collection page preset for the above product type, and obtain the target product distribution ratio in the collection page preset for the above product type, so that the terminal can obtain the target relative position of the above product type according to the above target product area position and the target product area distribution ratio. Among them, the target product area position can be the position of the product area where the terminal expects the product to be collected in the above collection page, and the target product distribution ratio can be the uniformity of the distribution of the product area where the terminal expects the product to be collected in the above collection page. Specifically, the terminal can divide the collection page into multiple areas, and the terminal determines the product area distribution ratio based on the proportion of the product area distributed in each area of the collection page.

[0066] For the target relative size, the terminal can obtain the target product area size in the collection page preset for the above product type. Thus, the terminal can determine the target relative size according to the above target product area size. Among them, the target product area size can be the area size of the above product area in the above collection page. The above target product area size can be a fixed value or a value range. The terminal can obtain the preset collection rule corresponding to the above product type according to the above target relative position and the target relative size.

[0067] Specifically, the above products can include multiple types. For example, the product types can include, but are not limited to, daily chemicals, alcoholic beverages, drinks, milk powder, grain and oil, etc. The above product area can be a product frame displayed on the collection page. Then, the above target product area position can represent the distribution position of the product frame, and the target product area distribution ratio can represent the left-right and up-down distribution ratios of the product frame on the collection page; the target product area size can represent the maximum and minimum areas of the product frame. Moreover, in some embodiments, the above product types also correspond to display positions. Based on different display positions and different product types, the terminal considers aspects such as the distance, angle, and integrity between the terminal and the product, and combines collection methods such as taking pictures or videos to preset corresponding target relative positions and target relative sizes, forming a preset collection rule. For example, the collection rule can include product type, display position, shooting mode, verification items, and custom parameters, etc.

[0068] In one embodiment, the product types in the above collection rule can include types such as daily chemicals, alcoholic beverages, drinks, milk powder, grain and oil, etc.; the above display positions can include positions such as shelves, stackers, cold wind cabinets, and freezers, etc.; the above shooting modes can include modes such as taking pictures and videos; the above verification items can include distance, angle, and integrity, etc.; the above custom parameters can include the distribution position of the product frame, the maximum area of the product frame, the minimum area of the product frame, the left-right distribution ratio of the product frame, and the up-down distribution ratio of the product frame, etc. The terminal can build collection rules for different product types based on the above parameters.

[0069] Through this embodiment, the terminal can use the target relative position and target relative size corresponding to the product area of the product on the collection page to build a preset collection rule corresponding to the product type. Thus, the terminal uses the above preset collection rule to collect information on the products displayed in the logistics store, improving the efficiency of product information collection.

[0070] In one embodiment, inputting the preset collection rule and the collection page into a trained collection model includes: inputting the preset collection rule and the collection page into the trained collection model, and the collection model identifies the product area corresponding to the product to be collected on the collection page; according to the relative position of the product area on the collection page, outputs the corresponding position guidance information; the position guidance information is used to instruct the collector to adjust the relative position of the product area on the collection page; according to the relative size of the product area on the collection page, outputs the corresponding size guidance information; the size guidance information is used to instruct the collector to adjust the relative size of the product area on the collection page.

[0071] In this embodiment, the terminal can use the acquisition model to guide the acquirer to adjust the terminal to the correct acquisition posture. The terminal can input the above preset acquisition rules and acquisition page into the trained acquisition model. The acquisition model can identify the product area of the product to be acquired in the acquisition page. Based on the above product area, the acquisition model can determine the relative position and relative size of the product area in the acquisition page. Thus, the acquisition model can output corresponding position guidance information according to the above relative position. Thus, the acquirer can adjust the relative position of the product area in the acquisition page to meet the target relative position by moving or adjusting the shooting angle of the terminal, etc.

[0072] The above acquisition model can also output corresponding size guidance information according to the relative size of the product area in the acquisition page. Thus, the acquirer can adjust the relative size of the product area in the acquisition page to meet the target relative size by moving or adjusting the shooting angle of the terminal, etc.

[0073] Specifically, as Figure 2 shown, Figure 2 it is a schematic diagram of the interface of the product information acquisition steps in an embodiment. Figure 2 It is an interface diagram of the acquisition page. Taking the product type as grains and oils and the display position as a stack head as an example, the terminal can use the above acquisition model to identify the product area in the acquisition page, such as Figure 2 the product frame 200 in it. Among them, there can be multiple product frames 200, each product can correspond to a product frame, and each product frame can represent a product type in one acquisition. For the target relative position, the terminal can judge the position and size based on a single product frame, or can also judge the position and size based on the overall frame formed by all product frames in the acquisition page.

[0074] For example, in some embodiments, taking Figure 2 the display position as a stack head as an example, the terminal can output acquisition angle guidance information for the stack head. Thus, the acquirer can adjust the display angle of the above stack head by moving or adjusting the shooting angle, etc. Among them, the display angle of the stack head can be determined based on the display angle of the overall frame surrounding all the product frames in the acquisition page. When the terminal detects that the overall frame surrounding all the product frames in the acquisition page is displayed within a 45° diagonal, it can be determined that the acquisition angle corresponding to the display position is met, so that for the stack head, the terminal shoots diagonally, so that two adjacent faces of the stack head can be photographed completely, ensuring the integrity of the product display.

[0075] In addition, in some embodiments, the terminal can also detect anomalies existing in the acquisition page in real time, and guide the acquisition personnel to adjust the terminal by presenting problems and prompting operations on the front end. Common problems include, but are not limited to, left - right continuity, up - down integrity, shooting angle, shooting distance, etc. For example, as Figure 3 shown, Figure 3 FIG. is a schematic diagram of the interface for the guidance information output step in an embodiment. When the terminal does not detect the product frame through the acquisition model, it can output a prompt message of "product not detected", so that the acquisition personnel can, based on this prompt message, correct the anomaly by moving or adjusting the shooting angle of the terminal, etc. And, in some embodiments, the terminal can also accumulate the number of anomalies and the correction situation during the acquisition process. When the number of anomalies is greater than the preset anomaly number threshold, or the number of corrections is less than the preset correction number threshold, the terminal can forcibly interrupt the acquisition and restart the acquisition process for this product to ensure the quality of the acquisition.

[0076] Through the above - mentioned embodiments, the terminal can, based on the acquisition model and the preset acquisition rules, dynamically output corresponding guidance information in real time during the acquisition process for different product types, enabling the acquisition personnel to adjust the terminal in a timely manner and improving the efficiency of product information acquisition.

[0077] In one embodiment, according to the relative position of the product area in the acquisition page, corresponding position guidance information is output, including: obtaining a preset acquisition area in the acquisition page; according to the position of the product area in the acquisition area and the distribution ratio of the product area in the acquisition area, outputting corresponding position guidance information; the position guidance information is used to instruct the acquisition personnel to adjust the acquisition angle so that the product area is within the acquisition area and the distribution ratio of the product area to the acquisition area meets the preset distribution ratio.

[0078] In this embodiment, the terminal can use the acquisition model to output guidance for the relative position of the product area in the acquisition page. Among them, to ensure the integrity of the product in the acquisition page, an acquisition area can be preset in the acquisition page. Then the terminal can, through the acquisition model, based on the position of the above - mentioned product area in the acquisition area and the distribution ratio of the product area in the acquisition area, output corresponding position guidance information. Among them, the above - mentioned acquisition personnel can, based on the above - mentioned position guidance information, adjust the acquisition angle of the terminal so that the above - mentioned product area is within the acquisition area and the distribution ratio of the product area to the acquisition area meets the preset distribution ratio. Among them, the distribution ratio represents the proportion of the product area in each part of the acquisition area.

[0079] Specifically, as Figure 2As shown, the acquisition page can be the screen of the terminal. Taking the screen height as H, for example, the terminal can form the acquisition area 202 by setting the upper boundary of the screen, such as 0.05H, and the lower boundary of the screen, such as 0.95H. The above product area cannot exceed the upper and lower boundaries in the set acquisition area 202 to control the position and integrity of the product in the picture. For the distribution ratio, the terminal can Figure 2 combine all product frames in it into an overall product frame, and take the center of the screen as the dividing line to divide the overall product frame. Then calculate the ratio of the overall product frame after division in the upper half of the screen to the overall product frame after division in the lower half of the screen. If this ratio is greater than the preset ratio, the terminal can output the corresponding position guidance information, so that the acquisition personnel can adjust the shooting angle to make the product frames evenly distributed within the acquisition area. It should be noted that the above division can be achieved in various ways, such as dividing the screen into left and right halves, or dividing it into four quadrants representing four parts, etc.

[0080] Among them, during the above acquisition process, it can also include the guidance information output for various position anomalies. For example, as Figure 4 shown, Figure 4 is a schematic diagram of the interface of the guidance information output step in another embodiment. If the terminal detects through the acquisition model that in the above product area, the product in a certain part is incomplete, for example, the lower product is incomplete, the terminal can prompt information such as adjusting the shooting angle and shooting distance, so that the acquisition personnel can adjust their shooting angle and distance to make the product display completely. As Figure 5 shown, Figure 5 is a schematic diagram of the interface of the guidance information output step in yet another embodiment. When the terminal detects through the acquisition model that the distribution ratio of the above product area in the acquisition page is unbalanced, for example, it detects that the left and right ratios of the product area in the acquisition page differ too much, the terminal can output prompt information such as the shooting angle being too large. Based on this prompt information, the acquisition personnel can adjust their shooting angle to make the product area evenly distributed in the acquisition page.

[0081] Through this embodiment, the terminal can, based on the acquisition model and the preset acquisition rules, dynamically output the corresponding position guidance information in real time for different product types during the acquisition process, enabling the acquisition personnel to adjust the terminal in a timely manner, ensuring that the position of the product in the acquisition page meets the acquisition requirements, and improving the efficiency of product information acquisition.

[0082] In one embodiment, corresponding size guidance information is output according to the relative size of the product area in the acquisition page, including: obtaining the page size of the acquisition page and the area size of the product area in the acquisition page; outputting corresponding size guidance information according to the area size; the size guidance information is used to instruct the acquisition personnel to adjust the acquisition distance so that the ratio of the area size to the page size meets a preset ratio.

[0083] In this embodiment, the terminal can use the acquisition model to adjust the relative size of the product area in the acquisition page in combination with the above acquisition rules. The terminal can obtain the page size of the above acquisition page and the area size of the above product area in the acquisition page, so that the terminal can output corresponding size guidance information through the acquisition model in combination with the above area size. Among them, the acquisition model can output the above size guidance information when it detects that the area size is too large or too small, so that the acquisition personnel can adjust the acquisition distance based on the above size guidance information. For example, adjust the distance between the terminal and the product so that the ratio of the above area size to the above page size meets a preset ratio.

[0084] Specifically, as Figure 2 shown, the above product area may be the product frame 200. Taking the acquisition page, that is, the area of the mobile phone screen is S, and the target product area size in the acquisition rule is 0.05S as an example, the terminal can use the acquisition model to detect the area of the product frame 200 and output corresponding prompt information when the area is too small or too large. Among them, the target product area sizes corresponding to different products may be different.

[0085] The above size prompt information may specifically be as Figure 6 shown, Figure 6 For another embodiment, it is a schematic diagram of the interface of the guidance information output step. Taking the area being too small as an example, when the terminal detects that the area size of the above product frame 600 is smaller than the corresponding target area size, for example, 0.05S, it can output information such as the product frame is too small and the shooting distance is too far, so that the acquisition personnel can approach the product to be acquired according to this information, so that the product area in the acquisition page meets 0.05S.

[0086] The above different types of products can correspond to different acquisition rules. Based on the above various embodiments, taking the product type of grain and oil as an example, the following acquisition rules can be obtained: "Product type: Grain and oil; Display location: Stack; Shooting mode: Photographing; Verification items: {Integrity: [Parameter name: Product frame distribution position (parameter value: 0.05H, 0.95H)], Distance: [Maximum area of product frame (parameter value: 0.05S)], Distance: [Minimum area of product frame (parameter value: 0.01S)], Angle: [Vertical distribution ratio (parameter value: 2:3)]}". Among them, "Distance: [Maximum area of product frame (parameter value: 0.05S)]" means that when the area of the product frame exceeds 0.05S, the terminal outputs distance adjustment information; "Angle: [Vertical distribution ratio (parameter value: 2:3)]" means that when the distribution ratio of the product frame is too different from 2:3, the terminal outputs angle adjustment information.

[0087] Through this embodiment, the terminal can, based on the acquisition model and the preset acquisition rules, for different product types, dynamically output corresponding size guidance information in real time during the acquisition process, enabling the acquisition personnel to adjust the terminal in a timely manner, ensuring that the regional size of the product meets the acquisition requirements, and improving the efficiency of product information acquisition. Moreover, by providing reminder information in real time during the acquisition process, the execution threshold of the acquisition task is also reduced, and the quality and efficiency of product information acquisition in the logistics store are improved.

[0088] It should be understood that although the steps in the flowcharts involved in the above various embodiments are shown in sequence according to the arrows, these steps do not necessarily need to be executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above various embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily need to be executed at the same time, but can be executed at different times. The execution order of these steps or stages does not necessarily need to be sequential, but can be executed alternately or in turn with at least a part of the steps or stages in other steps or other steps.

[0089] Based on the same inventive concept, an embodiment of the present application further provides a product information acquisition device for implementing the product information acquisition method involved above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the product information acquisition device provided below can refer to the limitations on the product information acquisition method in the above text, and will not be repeated here.

[0090] In one embodiment, as Figure 7As shown, a product information collection device is provided, including: a response module 500, an acquisition module 502, a guidance module 504, and a collection module 506, where:

[0091] The response module 500 is configured to respond to an information collection instruction, display a collection page, and obtain the product type of the product to be collected.

[0092] The acquisition module 502 is configured to obtain a preset collection rule corresponding to the product type; the preset collection rule includes the target relative position and the target relative size of the product to be collected on the collection page.

[0093] The guidance module 504 is configured to input the preset collection rule and the collection page into a trained collection model. The collection model identifies the product area corresponding to the product to be collected on the collection page, and outputs corresponding guidance information according to the product area, the target relative position, and the target relative size; the guidance information is used to instruct the collector to adjust the relative position and the relative size of the product area on the collection page.

[0094] The collection module 506 is configured to collect the product information of the product to be collected in the product area when the product area meets the target relative position and the target relative size.

[0095] In one embodiment, the above-mentioned acquisition module 502 is configured to obtain the target product area position in the collection page preset for the product type, and the target product area distribution ratio in the collection page, and obtain the target relative position according to the target product area position and the target product area distribution ratio; obtain the target product area size preset for the product type in the collection page, and determine the target relative size according to the target product area size; obtain the preset collection rule corresponding to the product type according to the target relative position and the target relative size.

[0096] In one embodiment, the above-mentioned guidance module 504 is configured to input the preset collection rule and the collection page into a trained collection model. The collection model identifies the product area corresponding to the product to be collected in the collection page; outputs corresponding position guidance information according to the relative position of the product area in the collection page; the position guidance information is used to instruct the collector to adjust the relative position of the product area in the collection page; outputs corresponding size guidance information according to the relative size of the product area in the collection page; the size guidance information is used to instruct the collector to adjust the relative size of the product area in the collection page.

[0097] In one embodiment, the above-mentioned guidance module 504 is configured to obtain a preset acquisition area in the acquisition page; output corresponding position guidance information according to the position of the product area in the acquisition area and the distribution ratio of the product area in the acquisition area; the position guidance information is used to instruct the acquisition personnel to adjust the acquisition angle so that the product area is within the acquisition area and the distribution ratio of the product area to the acquisition area meets a preset distribution ratio.

[0098] In one embodiment, the above-mentioned guidance module 504 is configured to obtain the page size of the acquisition page and the area size of the product area in the acquisition page; output corresponding size guidance information according to the area size; the size guidance information is used to instruct the acquisition personnel to adjust the acquisition distance so that the ratio of the area size to the page size meets a preset ratio.

[0099] In one embodiment, the above-mentioned guidance module 504 is configured to input a preset acquisition rule and an acquisition page into a trained acquisition model, and the acquisition model outputs corresponding acquisition angle guidance information according to the display position; the acquisition angle guidance information is used to instruct the acquisition personnel to adjust the acquisition angle so that the product area of the product to be acquired in the acquisition page meets a preset display angle.

[0100] In one embodiment, the above-mentioned acquisition module 506 is configured to detect the product coordinates of the product to be acquired in the acquisition page according to the product area when the product area meets the target relative position and the target relative size; determine the product information of the product to be acquired according to the product coordinates.

[0101] Each module in the above-mentioned product information acquisition device can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in the form of hardware or independent of it, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0102] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 8As shown in the figure. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be achieved through WIFI, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it realizes a product information collection method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0103] Those skilled in the art can understand that Figure 8 the structure shown in the figure is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0104] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, it realizes the above-mentioned product information collection method.

[0105] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, it realizes the above-mentioned product information collection method.

[0106] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, it realizes the above-mentioned product information collection method.

[0107] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties.

[0108] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0109] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0110] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A product information collection method, characterized in that, The method includes: In response to an information collection instruction, display a collection page and obtain the product type of the product to be collected; Obtain the preset collection rule corresponding to the product type; the preset collection rule includes the target relative position and the target relative size of the product to be collected on the collection page; Input the preset collection rule and the collection page into a trained collection model, and let the collection model identify the product area corresponding to the product to be collected on the collection page. According to the product area, the target relative position, and the target relative size, output corresponding guidance information; the guidance information is used to instruct the collector to adjust the relative position and relative size of the product area on the collection page; When the product area meets the target relative position and the target relative size, collect the product information of the product to be collected in the product area.

2. The method according to claim 1, characterized in that, The obtaining the preset collection rule corresponding to the product type includes: Obtain the target product area position preset for the product type on the collection page and the target product area distribution ratio on the collection page, and obtain the target relative position according to the target product area position and the target product area distribution ratio; Obtain the target product area size preset for the product type on the collection page, and determine the target relative size according to the target product area size; According to the target relative position and the target relative size, obtain the preset collection rule corresponding to the product type.

3. The method according to claim 2, characterized in that, The inputting the preset collection rule and the collection page into a trained collection model includes: Input the preset collection rule and the collection page into a trained collection model, and let the collection model identify the product area corresponding to the product to be collected on the collection page; Output corresponding position guidance information according to the relative position of the product area on the collection page; the position guidance information is used to instruct the collector to adjust the relative position of the product area on the collection page; Output corresponding size guidance information according to the relative size of the product area on the collection page; the size guidance information is used to instruct the collector to adjust the relative size of the product area on the collection page.

4. The method according to claim 3, characterized in that, The outputting corresponding position guidance information according to the relative position of the product area on the collection page includes: Obtain the preset collection area on the collection page; Output corresponding position guidance information according to the position of the product area in the collection area and the distribution ratio of the product area in the collection area; The position guidance information is used to instruct the collector to adjust the collection angle so that the product area is within the collection area and the distribution ratio of the product area to the collection area meets a preset distribution ratio.

5. The method according to claim 3, characterized in that, The outputting corresponding size guidance information according to the relative size of the product area on the collection page includes: Obtain the page size of the collection page and the area size of the product area on the collection page; Output corresponding size guidance information according to the area size; The size guidance information is used to instruct the collector to adjust the collection distance so that the ratio of the area size to the page size meets a preset ratio.

6. The method according to claim 1, characterized in that, The preset collection rule further includes the display position corresponding to the product type; the inputting the preset collection rule and the collection page into the trained collection model includes: Inputting the preset collection rule and the collection page into the trained collection model, and the collection model outputs corresponding collection angle guidance information according to the display position; the collection angle guidance information is used to instruct the collector to adjust the collection angle so that the product area of the product to be collected in the collection page meets a preset display angle.

7. The method according to any one of claims 1 to 6, characterized in that, The collecting the product information of the product to be collected in the product area when the product area meets the target relative position and the target relative size includes: When the product area meets the target relative position and the target relative size, detecting the product coordinates of the product to be collected in the collection page according to the product area; Determining the product information of the product to be collected according to the product coordinates.

8. A product information collection device, characterized in that, The device includes: A response module, configured to respond to an information collection instruction, display a collection page, and obtain the product type of the product to be collected; An acquisition module, configured to acquire the preset collection rule corresponding to the product type; the preset collection rule includes the target relative position and the target relative size of the product to be collected in the collection page; A guidance module, configured to input the preset collection rule and the collection page into the trained collection model, the collection model identifies the product area corresponding to the product to be collected in the collection page, and outputs corresponding guidance information according to the product area, the target relative position, and the target relative size; the guidance information is used to instruct the collector to adjust the relative position and the relative size of the product area in the collection page; A collection module, configured to collect the product information of the product to be collected in the product area when the product area meets the target relative position and the target relative size.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images