Goods warehousing interaction method and system applicable to multi-dimensional data model

Abstract

The present invention provides a goods warehousing interaction method and system suitable for a multidimensional data model, comprising: when the server determines that it has received a warehousing demand from a first warehousing end, the server sends the warehousing demand to the multidimensional data model, and the multidimensional data model has a pre-configured warehousing strategy and interaction method; determines a corresponding warehousing strategy and feeds it back to the corresponding first warehousing end; the multidimensional data model generates a corresponding interaction path based on the interaction method corresponding to the warehousing demand, the interaction starting point in the interaction path corresponds to the first warehousing end, and other interaction nodes in the interaction path correspond to other warehousing management ends; after the multidimensional data model determines that it has received the warehousing data extracted by the first warehousing end and the interaction data fed back by the warehousing management end, the multidimensional data model feeds back the corresponding warehousing demand to the server so that the server completes the warehousing record.

Description

Technical Field

[0001] The present invention relates to data processing technology, and in particular to a goods warehousing interaction method and system suitable for a multi-dimensional data model. Background Art

[0002] In modern logistics and warehouse management systems, the efficient storage of goods is a challenging task, especially when dealing with data of multiple types and sources.

[0003] Traditional warehousing systems often rely on a single data input method, such as manual input or basic barcode scanning, which cannot efficiently handle complex or changing warehousing requirements. In addition, traditional systems often lack flexibility and cannot automatically adjust warehousing strategies according to the characteristics of different goods, resulting in low warehousing efficiency and failure to meet modern high-efficiency requirements.

[0004] Therefore, how to automatically adjust the warehousing strategy according to the characteristics of different goods, improve warehousing efficiency, and meet the requirements of modern high efficiency has become an urgent problem to be solved. Summary of the invention

[0005] The embodiments of the present invention provide a method and system for goods warehousing interaction applicable to a multi-dimensional data model, which can automatically adjust the warehousing strategy according to the characteristics of different goods, improve the warehousing efficiency, and meet the requirements of modern high efficiency.

[0006] According to a first aspect of an embodiment of the present invention, there is provided a goods warehousing interaction method applicable to a multi-dimensional data model, comprising:

[0007] When the server determines that it has received the warehousing demand from the first warehousing end, it sends the warehousing demand to the multidimensional data model, wherein the multidimensional data model has a pre-configured warehousing strategy and interaction method, and the warehousing strategy includes at least one of an image extraction sub-strategy, a voice extraction sub-strategy and / or a text extraction sub-strategy;

[0008] The multi-dimensional data model analyzes the warehousing demand, determines a customized warehousing strategy and feeds it back to the corresponding first warehousing end, so that the first warehousing end extracts information about the warehousing target according to the warehousing strategy;

[0009] The multidimensional data model generates a corresponding interaction path based on the interaction method corresponding to the warehousing demand, wherein the interaction starting point in the interaction path corresponds to the first warehousing end, and other interaction nodes in the interaction path correspond to other warehousing management ends;

[0010] After determining that the multi-dimensional data model has received the storage data extracted by the first storage end and the interactive data fed back by the storage management end, the multi-dimensional data model feeds back the corresponding storage demand to the server so that the server completes the storage record.

[0011] Optionally, in a possible implementation of the first aspect, when the server determines that it has received the warehousing demand from the first warehousing end, the server sends the warehousing demand to the multidimensional data model, and the multidimensional data model has a pre-configured warehousing strategy and interaction method, including:

[0012] When the server determines that it has received the warehousing demand from the first warehousing end, it extracts the warehousing item label corresponding to the warehousing demand and sends it to the multi-dimensional data model;

[0013] The multidimensional data model determines the corresponding warehousing strategy and interaction method based on the warehousing item label, and each warehousing item label has a preset warehousing strategy and interaction method; the multidimensional data model analyzes the warehousing demand, determines a customized warehousing strategy and feeds it back to the corresponding first warehousing end, so that the first warehousing end extracts information on the warehousing target according to the warehousing strategy, including:

[0014] The multi-dimensional data model extracts the storage strategy for the storage item label, wherein the storage strategy includes at least one of an image extraction sub-strategy, a voice extraction sub-strategy and / or a text extraction sub-strategy;

[0015] Generate a customized information extraction template with an information extraction identifier based on the type information and quantity information of the sub-strategies in the warehousing strategy, and feed it back to the first warehousing end;

[0016] The first warehousing end interacts with the information extraction template based on the information extraction identifier to extract information from the warehousing target.

[0017] Optionally, in a possible implementation of the first aspect, generating an information extraction template with an information extraction identifier based on the type information and quantity information of the sub-strategies in the warehousing strategy, and feeding back the information to the first warehousing end, includes:

[0018] If it is determined that the warehousing strategy includes an image extraction sub-strategy, the image sub-model in the multi-dimensional data model obtains the warehousing category corresponding to the warehousing item label, and analyzes and processes the historical data of the warehousing category to obtain the historical image extraction features corresponding to the warehousing category;

[0019] Acquire a feature label corresponding to each historical image extraction feature, and filter and process the feature label to obtain a target feature label, wherein the feature label includes at least a view label and a loss label;

[0020] The image sub-model extracts the target view label and the target loss label corresponding to the target feature label, and establishes a corresponding image slot in the information extraction template based on the target view label and the target loss label.

[0021] Optionally, in a possible implementation manner of the first aspect, acquiring a feature label corresponding to each historical image extraction feature, filtering and processing the feature label to obtain a target feature label, wherein the feature label at least includes a view label and a loss label, comprises:

[0022] Count the number of abnormal wear labels in each view label among all historical image extraction features of the same type of warehoused item labels, and count the number of normal wear labels in each view label;

[0023] Generating a loss weight of each loss label based on the description information of the loss label, each description information having a preset loss weight;

[0024] A calculation is performed based on the abnormal number, the normal number and the loss weight to obtain a feature label coefficient corresponding to the historical image extraction feature, and a target feature label is determined from multiple feature labels based on the feature label coefficient.

[0025] Optionally, in a possible implementation manner of the first aspect, the calculating based on the abnormal number, the normal number, and the loss weight to obtain a feature label coefficient corresponding to the historical image extraction feature, and determining a target feature label from multiple feature labels based on the feature label coefficient includes:

[0026] Adding the abnormal number to the normal number to obtain the total number, performing ratio calculation based on the abnormal number and the total number to obtain the abnormal ratio, and performing calculation based on the abnormal ratio, the preset ratio, and the preset number to obtain the calculated number;

[0027] Obtain the loss weight of the loss label corresponding to each view label, and add the loss weights of the loss labels corresponding to the same type of view labels to obtain the average loss weight;

[0028] Based on the average loss weight and the number of abnormal loss labels corresponding to each type of view label, a feature label coefficient of the corresponding type is calculated;

[0029] A target feature label is determined from among a plurality of feature labels based on the calculation quantity and the feature label coefficient.

[0030] Optionally, in a possible implementation manner of the first aspect, determining a target feature tag from a plurality of feature tags based on the calculated quantity and the feature tag coefficient quotient includes:

[0031] Sorting the plurality of feature labels in descending order based on the feature label coefficients to obtain a corresponding descending sorting sequence;

[0032] According to the calculated quantity, the feature labels of the calculated quantity are sequentially traversed in the descending sort sequence to be selected as the determined target feature labels;

[0033] The calculation quantity, average loss weight and feature label coefficient are obtained through the following formula:

[0034]

[0035] Among them, x cal To calculate the quantity, s abn is the abnormal quantity, the normal quantity s nor is the normal quantity, g is the preset constant value, b pre is the preset ratio, x pre is the preset quantity, is the feature label coefficient of the i-th type, u j is the loss weight corresponding to the jth feature label in the ith type, h is the upper limit of the number of features extracted from historical images corresponding to the feature label in the ith type, H is the number of features extracted from historical images corresponding to the feature label in the ith type, e i is the number of abnormal loss labels corresponding to the feature labels in the i-th type, g qua is the normalized value of quantity.

[0036] Optionally, in a possible implementation manner of the first aspect, the image sub-model extracts a target view label and a target loss label corresponding to the target feature label, and establishes a corresponding image slot in the information extraction template based on the target view label and the target loss label, including:

[0037] The image sub-model extracts a target view label and a target loss label corresponding to the target feature label, wherein the target loss label has a view loss position corresponding to the target view;

[0038] Proportionally positioning the loss position of the target view corresponding to the target view label based on the view loss position;

[0039] A primary image slot corresponding to the target view is established at the information extraction template, and a secondary slot recognition area for the target view is generated based on the proportional positioning distribution of all target feature labels in all historical target views, and a corresponding secondary image slot is established at the primary image slot.

[0040] Optionally, in a possible implementation manner of the first aspect, proportionally locating the loss position of the target view corresponding to the target view label based on the view loss position includes:

[0041] Acquire a loss view corresponding to the view loss position, perform coordinate processing on the target view according to a preset point as the origin, and acquire the corner point coordinates of a preset corner point of the target view;

[0042] Extracting the first X-axis value and the first Y-axis value corresponding to the corner point coordinates to generate the corresponding first X-axis interval value and the first Y-axis interval value;

[0043] Acquire the second X-axis value and the second Y-axis value in the loss view to generate corresponding second X-axis interval value and second Y-axis interval value;

[0044] Proportional positioning of the X-axis is performed based on the first X-axis interval value and the second X-axis interval, and proportional positioning of the Y-axis is performed based on the first Y-axis interval value and the second Y-axis interval.

[0045] Optionally, in a possible implementation manner of the first aspect, extracting a corresponding first X-axis value and a first Y-axis value from the corner point coordinates to generate a corresponding first X-axis interval value and a first Y-axis interval value includes:

[0046] Extracting the largest first X-axis value and the smallest first X-axis value in the corner point coordinates to obtain corresponding first X-axis interval values;

[0047] Extracting the largest first Y-axis value and the smallest first Y-axis value in the corner point coordinates to obtain corresponding first Y-axis interval values;

[0048] The step of acquiring the second X-axis value and the second Y-axis value in the loss view to generate corresponding second X-axis interval value and second Y-axis interval value comprises:

[0049] Extract the maximum second X-axis value and the minimum second X-axis value in the loss view to obtain the corresponding second X-axis interval value;

[0050] Extracting the maximum second Y-axis value and the minimum second Y-axis value in the loss view to obtain corresponding second Y-axis interval values; performing proportional positioning of the X-axis based on the first X-axis interval value and the second X-axis interval, and performing proportional positioning of the Y-axis based on the first Y-axis interval value and the second Y-axis interval, including:

[0051] Determine the X-axis segments of the second X-axis interval that overlap with the values ​​of the first X-axis interval, and determine the Y-axis segments of the second Y-axis interval that overlap with the values ​​of the first Y-axis interval;

[0052] Proportional positioning is performed on the loss position of the target view according to the overlapping X-axis segments and the overlapping Y-axis segments, and the proportional positioning area is highlighted.

[0053] A second aspect of an embodiment of the present invention provides a goods warehousing interactive system applicable to a multi-dimensional data model, including:

[0054] A judgment module, configured to enable the server to send the warehousing demand to the multidimensional data model when judging that the server has received the warehousing demand from the first warehousing end, wherein the multidimensional data model has a pre-configured warehousing strategy and an interaction method, and the warehousing strategy includes at least one of an image extraction sub-strategy, a voice extraction sub-strategy and / or a text extraction sub-strategy;

[0055] An analysis module is used to enable the multi-dimensional data model to analyze the warehousing demand, determine the corresponding warehousing strategy and feed it back to the corresponding first warehousing end, so that the first warehousing end extracts information about the warehousing target according to the warehousing strategy;

[0056] A generation module, configured to enable the multi-dimensional data model to generate a corresponding interaction path based on the interaction method corresponding to the warehousing demand, wherein the interaction starting point in the interaction path corresponds to the first warehousing end, and other interaction nodes in the interaction path correspond to other warehousing management ends;

[0057] The extraction module is used to enable the multi-dimensional data model to feed back the corresponding warehousing demand to the server after judging that it has received the warehousing data extracted by the first warehousing end and the interactive data fed back by the warehousing management end so that the server can complete the warehousing record.

[0058] Technical effects:

[0059] 1. The present invention improves warehousing efficiency and accuracy. The multidimensional data model of the present invention can automatically select the most appropriate warehousing strategy according to the different characteristics of the goods (such as images, voice, and text information). Through the pre-configured multiple warehousing sub-strategies, the system can quickly formulate and execute warehousing plans for different goods, significantly improving warehousing efficiency and accuracy. At the same time, the present invention can generate corresponding interaction paths. This method can significantly improve the speed and accuracy of warehousing operations and reduce human errors. Enhance the flexibility and adaptability of the system. This method enhances the adaptability of the system to different warehousing requirements by introducing a multidimensional data model that can analyze multiple data types. Whether it is image data, sound or text labels, the system can recognize and adjust the interaction strategy according to the specific content, so that it can flexibly respond to changing logistics needs.

[0060] 2. The present invention greatly optimizes the automated process of goods entering the warehouse through multi-dimensional data models and highly customized information extraction templates, thereby significantly improving the efficiency and accuracy of entering the warehouse. Specifically, the system not only realizes efficient data processing in traditional logistics and warehouse management systems, but also improves information flow and processing consistency through innovative interactive path generation mechanisms. Through the collaborative work of components such as image sub-models, the system is able to accurately identify visual and wear information of warehoused items. For example, the system automatically identifies and selects the most critical views and wear labels by analyzing image features in historical data, thereby optimizing the accuracy of information extraction. In addition, the model effectively screens out image features that best match the current situation of warehoused items through the calculation of feature label coefficients, further improving the accuracy and reliability of warehoused data.

[0061] 3. The customized operation process of the present invention can dynamically generate information extraction templates containing necessary information slots according to different warehousing requirements. These templates are optimized according to the characteristics of the goods and the warehousing strategy. This customized process not only enhances the flexibility of the system, but also ensures that all kinds of goods can be processed quickly and accurately as needed. The use of information extraction templates reduces the complexity of operations, so that the first warehousing end can efficiently complete the task even without complex training, which significantly improves work efficiency. In addition, the present invention also enhances the interactive data flow and tracking capabilities, and the efficient data interaction between multiple warehousing ends, through the innovative interactive path generation mechanism, not only optimizes the information flow, but also ensures the coherence and consistency of data processing. The design of this system makes the entire warehousing process more systematic and traceable, greatly improving the transparency of operations and error tracking capabilities. In addition, the system can feedback interactive data and warehousing requirements to the server in real time, further ensuring the real-time update and accurate recording of data, which is of great value for inventory management and future strategy formulation. In summary, this patented technology significantly improves the efficiency and accuracy of goods warehousing through the deep integration of multi-dimensional data models and the application of intelligent information extraction templates, while also enhancing the flexibility and adaptability of the system, providing an innovative and efficient solution for modern warehouse management systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 A flowchart of a method for interacting with goods entering a warehouse in a multi-dimensional data model provided by an embodiment of the present invention;

[0063] Figure 2 A schematic diagram showing a coordinate interval provided by an embodiment of the present invention;

[0064] Figure 3 A schematic diagram of an information extraction template provided by an embodiment of the present invention;

[0065] Figure 4 A structural schematic diagram of a goods warehousing interactive system suitable for a multi-dimensional data model provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein.

[0068] It should be understood that in various embodiments of the present invention, the size of the sequence number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0069] It should be understood that in the present invention, "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0070] It should be understood that in the present invention, "plurality" refers to two or more than two. "And / or" is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "Contains A, B and C", "Contains A, B, C" means that A, B, and C are all included, "Contains A, B or C" means that one of A, B, and C is included, and "Contains A, B and / or C" means that any one, any two, or any three of A, B, and C are included.

[0071] It should be understood that in the present invention, "B corresponding to A", "B corresponding to A", "A corresponds to B" or "B corresponds to A" means that B is associated with A and B can be determined based on A. Determining B based on A does not mean determining B based only on A, but B can also be determined based on A and / or other information. A and B match when the similarity between A and B is greater than or equal to a preset threshold.

[0072] Depending on the context, "if" as used herein may be interpreted as "when" or "when" or "in response to determining" or "in response to detecting."

[0073] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0074] See also Figure 1 , is a flow chart of a method for goods warehousing interaction applicable to a multi-dimensional data model provided by an embodiment of the present invention, including:

[0075] S1, when the server determines that it has received an entry requirement from the first entry end, it sends the entry requirement to the multidimensional data model, and the multidimensional data model has a pre-configured entry strategy and interaction method. The entry strategy includes at least one of an image extraction sub-strategy, a voice extraction sub-strategy and / or a text extraction sub-strategy.

[0076] The first warehousing end may be held by the warehousing personnel, and when they have warehousing requirements, they can use the above-mentioned multi-dimensional data model to perform automated operations. The multi-dimensional data model is a pre-configured data processing model that can execute corresponding data processing and interaction strategies according to different requirements. The multi-dimensional data model contains different sub-strategies for processing different types of data (such as images, voice, and text).

[0077] In some embodiments, when the server determines that it has received the warehousing demand from the first warehousing end, it sends the warehousing demand to the multi-dimensional data model, and the multi-dimensional data model has a pre-configured warehousing strategy and interaction method, including:

[0078] S11, when the server determines that it has received a warehousing demand from the first warehousing end, it extracts the warehousing item label corresponding to the warehousing demand and sends it to the multi-dimensional data model.

[0079] The server first needs to determine whether it has received a warehousing demand from the first warehousing end (such as an interface of an automated logistics system, input from a warehousing person). Once the warehousing demand is confirmed, the server extracts the warehousing item label information related to the demand. It is worth mentioning that the warehousing items have a corresponding warehousing item label set in advance.

[0080] S12, the multi-dimensional data model determines corresponding storage strategies and interaction methods based on the storage item labels, and each storage item label has a preset storage strategy and interaction method.

[0081] It is understandable that different warehoused items have different warehoused strategies and interaction methods. This solution can make judgments based on the warehoused item labels. For example, item A needs to process the warehoused data of images and voices; item B needs to process the warehoused data of images and texts. Different warehoused strategies are used to process different types of data (such as images, voices, and texts).

[0082] Through the warehousing process of the multi-dimensional data model of this solution, the server can efficiently and intelligently handle different types of warehousing requirements, ensuring accurate classification and storage of data. Such a system improves the operating efficiency of automated warehouses and reduces human errors. In addition, the preset strategies and methods make the system more sophisticated and professional in handling different items.

[0083] S2, the multi-dimensional data model analyzes the warehousing demand, determines a customized warehousing strategy and feeds it back to the corresponding first warehousing end, so that the first warehousing end extracts information about the warehousing target according to the warehousing strategy.

[0084] The multidimensional data model is an automated processing model that can perform detailed analysis of warehousing requirements and generate customized warehousing strategies to guide the first warehousing end to perform effective information extraction.

[0085] In some embodiments, the multi-dimensional data model analyzes the warehousing demand, determines a customized warehousing strategy, and feeds it back to the corresponding first warehousing end, so that the first warehousing end extracts information about the warehousing target according to the warehousing strategy, including:

[0086] S21, the multi-dimensional data model extracts the storage strategy for the storage item label, and the storage strategy includes at least one of an image extraction sub-strategy, a voice extraction sub-strategy and / or a text extraction sub-strategy.

[0087] The multi-dimensional data model first analyzes the labels of the incoming items and extracts the relevant warehousing strategies. It is understandable that some items require image information collection when entering the warehouse, such as physical equipment; some items require voice and / or text collection when entering the warehouse, and different items have different pre-set requirements.

[0088] S22, generating a customized information extraction template with an information extraction identifier based on the type information and quantity information of the sub-strategies in the warehousing strategy, and feeding back the template to the first warehousing end.

[0089] This solution will generate an information extraction template based on the type and quantity information of the sub-strategies, which has an information extraction mark. This template is then fed back to the first warehousing end to guide the information extraction process.

[0090] The step of generating an information extraction template with an information extraction identifier based on the type information and quantity information of the sub-strategies in the warehousing strategy and feeding it back to the first warehousing end includes:

[0091] S221, if it is determined that the warehousing strategy includes an image extraction sub-strategy, the image sub-model in the multi-dimensional data model obtains the warehousing category corresponding to the warehousing item label, and analyzes and processes the historical data of the warehousing category to obtain the historical image extraction features corresponding to the warehousing category.

[0092] If the entry strategy includes an image extraction sub-strategy, the image sub-model of the multidimensional data model will analyze the historical data of the category corresponding to the entry item label. Through this analysis, the multidimensional data model determines the historical image extraction features related to the entry category. It can be understood that the entry requirements of the same entry item label are roughly similar, so this solution will combine the historical image extraction features to determine the data to be extracted during this entry.

[0093] S222, obtaining feature labels corresponding to the extracted features of each historical image, filtering and processing the feature labels to obtain target feature labels, wherein the feature labels at least include view labels and loss labels.

[0094] The multi-dimensional data model obtains the feature labels corresponding to each historical image feature and filters and processes them to obtain target feature labels. These feature labels include at least view labels (such as top view and side view of the item) and wear labels (such as the damage of the item).

[0095] The step of obtaining a feature label corresponding to each feature extracted from each historical image and filtering and processing the feature label to obtain a target feature label, wherein the feature label includes at least a view label and a loss label, includes:

[0096] Count the number of abnormal wear labels in each view label among all historical image extraction features of the same type of warehoused item labels, and count the number of normal wear labels in each view label. This step mainly counts the number of abnormal wear labels in each view label. It can be understood that the more abnormal wear labels are, the greater the probability that the image corresponding to the corresponding view label is prone to problems, and the surface of the equipment that is prone to wear can be found; at the same time, this solution will also count the number of normal wear labels in each view label. It can be understood that the more normal wear labels are, the smaller the probability that the content corresponding to the image corresponding to the corresponding view label is prone to problems, and the surface of the equipment that is not prone to wear can be found.

[0097] The wear weight of each wear label is generated based on the description information of the wear label, and each description information has a preset wear weight. The description information of the wear label may be, for example, slight wear, medium wear, severe wear, etc. Each wear label has a preset wear weight according to its description information, which may be preset by the warehouse personnel based on experience, wherein the wear weight corresponding to severe wear may be greater than the wear weight corresponding to medium wear, and the wear weight corresponding to medium wear may be greater than the wear weight corresponding to slight wear.

[0098] Based on the abnormal number, normal number and loss weight, the characteristic label coefficient corresponding to the historical image extraction feature is calculated, and the target characteristic label is determined from multiple characteristic labels based on the characteristic label coefficient. This solution calculates the characteristic label coefficient, which is the calculation result based on the abnormal number, normal number and loss weight, and finally determines the target characteristic label by using these characteristic label coefficients. In the above manner, the first warehousing end can efficiently and automatically determine the warehousing target.

[0099] The calculation based on the abnormal number, the normal number and the loss weight is performed to obtain a feature label coefficient corresponding to the historical image extraction feature, and a target feature label is determined from multiple feature labels based on the feature label coefficient, including:

[0100] The total number is obtained by adding the number of exceptions to the normal number, the abnormal ratio is calculated based on the number of exceptions and the total number, and the calculated number is calculated based on the abnormal ratio, the preset ratio, and the preset number. It is understandable that the larger the number of exceptions, the larger the corresponding abnormal ratio. There will be relevant logic for obtaining the calculated number in the subsequent formula. Among them, the calculated number refers to the number of corresponding views, for example, 3 out of 6 views, so the larger the abnormal ratio, the larger the corresponding calculated number needs to be.

[0101] The loss weight of the loss label corresponding to each view label is obtained, and the loss weights of the loss labels corresponding to the same type of view labels are added and averaged to obtain the average loss weight. It can be understood that this solution will add the average loss weight of each view to obtain the average loss weight, for example, the left view corresponds to an average loss weight, and the right view corresponds to an average loss weight.

[0102] Based on the average loss weight and the number of abnormal loss labels corresponding to each type of view label, the corresponding type of feature label coefficient is calculated. It is worth mentioning that the more the number of abnormal loss labels corresponding to the corresponding type of view label, the greater the average loss weight, the greater the corresponding type of feature label coefficient, and the greater the feature label coefficient, the higher the degree of abnormality.

[0103] Based on the calculation quantity and the characteristic label coefficient, a target characteristic label is determined from the plurality of characteristic labels. This step is to comprehensively calculate the quantity and the characteristic label coefficient to obtain the target characteristic label.

[0104] The step of determining a target feature tag from a plurality of feature tags based on the calculation quantity and the feature tag coefficients includes:

[0105] Based on the feature tag coefficients, multiple feature tags are sorted in descending order to obtain a corresponding descending sorting sequence. It can be understood that in the above descending sorting sequence, the feature tag coefficients at the front are larger, and the larger the feature tag coefficients, the higher the abnormality.

[0106] According to the calculation quantity, the feature tags of the calculation quantity are sequentially traversed in the descending sort sequence to be selected as the determined target feature tags. After the calculation quantity is determined, this solution needs to find the feature tags of the corresponding quantity in the descending sort sequence in combination with the calculation quantity as the determined target feature tags to determine the views to be collected.

[0107] The calculation quantity, average loss weight and feature label coefficient are obtained through the following formula:

[0108]

[0109] Among them, x cal To calculate the quantity, s abn is the abnormal quantity, the normal quantity S nor is the normal quantity, g is the preset constant value, b pre is the preset ratio, x pre is the preset quantity, is the feature label coefficient of the i-th type, u jis the loss weight corresponding to the jth feature label in the ith type, h is the upper limit of the number of features extracted from historical images corresponding to the feature label in the ith type, H is the number of features extracted from historical images corresponding to the feature label in the ith type, e i is the number of abnormal loss labels corresponding to the feature labels in the i-th type, g qua is the normalized value of quantity.

[0110] In the above formula for calculating the quantity, Represents the abnormal proportion. The larger the number of abnormalities, the higher the abnormal proportion. Finally, the difference coefficient is obtained by combining the difference with the preset proportion. Then, the preset number is offset and adjusted to obtain the corresponding calculation number. The preset number can be 3, for example, which can be preset by the staff. This indicates that the abnormal ratio is less than the preset ratio. In this case, the preset number can be used as the calculation number. This indicates that the abnormal ratio is greater than or equal to the preset ratio. In this case, the preset number can be increased and adjusted to obtain the calculated number. If the calculated number is not an integer, it can be rounded up.

[0111] In the above formula for obtaining the feature label coefficient, represents the average loss weight, the number of abnormal loss labels corresponding to the feature label in the i-th type e i The larger the value is, the greater the abnormality of the corresponding view type is, and the larger the final feature label coefficient will be. The quantity normalization value can be preset by the staff.

[0112] S223, the image sub-model extracts the target view label and the target loss label corresponding to the target feature label, and establishes the corresponding image slot in the information extraction template based on the target view label and the target loss label. It should be noted that the target feature label will include a target view label and a target loss label, and the target view label will correspond to the corresponding view, such as the front view, side view, top view, etc. Each target view label will have a corresponding target loss label, and the target loss label can be the view corresponding to the loss in the front view, side view, and top view, respectively.

[0113] Among them, the target view label is, for example, the front view of device A, and the target wear label is, for example, a local part in the front view that is more susceptible to wear and tear. Then, the corresponding image slot is established in the information extraction template in combination with the above data. Through this process, the first warehousing end can efficiently and accurately extract information about the incoming target. The information extraction template provides a mechanism that enables the first warehousing end to accurately extract and classify relevant information of the incoming items, such as image features and wear and tear conditions. This helps to optimize inventory management, improve the overall efficiency of the automated warehouse system, and reduce the possibility of errors.

[0114] The image sub-model extracts a target view label and a target loss label corresponding to the target feature label, and establishes a corresponding image slot in the information extraction template based on the target view label and the target loss label, including:

[0115] The image sub-model extracts a target view label and a target loss label corresponding to the target feature label, wherein the target loss label has a view loss position corresponding to the target view, wherein the view loss position is, for example, the position of a local part in the front view.

[0116] Based on the view loss position, the loss position of the target view corresponding to the target view tag is proportionally located. This solution needs to locate the data to be collected in combination with the view loss position.

[0117] The proportional positioning of the loss position of the target view corresponding to the target view label based on the view loss position includes:

[0118] The loss view corresponding to the view loss position is obtained, and the target view is coordinate-processed with the preset point as the origin to obtain the corner point coordinates of the preset corner points of the target view. In which, taking the loss view as the front view as an example, the preset point is, for example, the lower left corner of the front view, the front view is coordinate-processed, and then the four preset corner points of the device outline in the front view are identified, and then the corner point coordinates of the preset corner points are determined.

[0119] In some embodiments, if the corresponding target device is a regular rectangle, the corresponding preset corner points are the four corner points of the rectangle; in other embodiments, if it is determined that the target device corresponding to the front view is an irregular rectangle, the coordinates of the four preset corner points do not correspond, so it is necessary to obtain the extreme value coordinates corresponding to the target device in the target view, and generate the corresponding corner point coordinates according to the maximum X value, minimum X value, maximum Y value, and minimum Y value in the extreme value coordinates. At this time, the target view is a simulated target view, including the corresponding target device but not completely corresponding.

[0120] See also Figure 2 , extract the first X-axis value and the first Y-axis value corresponding to the corner point coordinates to generate the corresponding first X-axis interval value and the first Y-axis interval value. After determining the corner point coordinates, this solution needs to find the first X-axis value and the first Y-axis value corresponding to the corner point coordinates, where the first X-axis value refers to the data value corresponding to the device in the horizontal direction, and the first Y-axis value refers to the data value corresponding to the device in the vertical direction.

[0121] The extracting the corresponding first X-axis value and the first Y-axis value from the corner point coordinates to generate the corresponding first X-axis interval value and the first Y-axis interval value includes:

[0122] The maximum first X-axis value and the minimum first X-axis value in the corner point coordinates are extracted to obtain the corresponding first X-axis interval value. The maximum first X-axis value and the minimum first X-axis value can form the first X-axis interval value.

[0123] The maximum first Y-axis value and the minimum first Y-axis value in the corner point coordinates are extracted to obtain the corresponding first Y-axis interval value. The maximum first Y-axis value and the minimum first Y-axis value can form the first X-axis interval value.

[0124] The second X-axis value and the second Y-axis value in the loss view are obtained to generate corresponding second X-axis interval values ​​and second Y-axis interval values.

[0125] Proportional positioning of the X-axis is performed based on the first X-axis interval value and the second X-axis interval value, and proportional positioning of the Y-axis is performed based on the first Y-axis interval value and the second Y-axis interval value.

[0126] After obtaining the first X-axis interval value and the second X-axis interval value, the proportional positioning of the X-axis is performed in combination with the first X-axis interval value and the second X-axis interval value. After obtaining the first Y-axis interval value and the second Y-axis interval value, the proportional positioning of the Y-axis is performed in combination with the first Y-axis interval value and the second Y-axis interval value.

[0127] In some embodiments, obtaining the second X-axis value and the second Y-axis value in the loss view to generate corresponding second X-axis interval value and second Y-axis interval value includes:

[0128] Extract the maximum second X-axis value and the minimum second X-axis value in the loss view to obtain the corresponding second X-axis interval value. The maximum second X-axis value and the minimum second X-axis value can form a second X-axis interval value. Among them, the first coordinate corresponds to the target view, and the loss view is a local area in the target view. The loss view is a view determined by personnel. This view is a standard rectangular view. At this time, no simulated rectangular processing is required. In actual application scenarios, the loss view may include multiple parts. Generally speaking, parts that are easily worn out will be located in the middle of the loss view. The loss view may also include other non-worn parts.

[0129] The maximum second Y-axis value and the minimum second Y-axis value in the loss view are extracted to obtain the corresponding second Y-axis interval value. The maximum second Y-axis value and the minimum second Y-axis value can form the second Y-axis interval value.

[0130] The performing proportional positioning of the X-axis based on the first X-axis interval value and the second X-axis interval value, and the performing proportional positioning of the Y-axis based on the first Y-axis interval value and the second Y-axis interval value include:

[0131] Determine the X-axis segment where the second X-axis interval value overlaps with the first X-axis interval value, and determine the Y-axis segment where the second Y-axis interval value overlaps with the first Y-axis interval value. This solution requires finding duplicate data of the second X-axis interval value and the first X-axis interval value, and finding the overlapping data of the Y-axis.

[0132] Proportional positioning is performed at the loss position of the target view according to the overlapping X-axis segments and the overlapping Y-axis segments, and the proportional positioning area is highlighted. Since different staff members have different shooting habits, when shooting a certain device, the proportional size of the device shot by different personnel is different in the image, but the proportional relationship between each part in the device and the device is certain, so the present invention needs to adopt proportional positioning to determine the corresponding part in a device. This proportional method can make it possible to quickly locate the part according to the proportional relationship between the part and the device even if the multiple images taken have different sizes.

[0133] A primary image slot corresponding to the target view is established at the information extraction template, and a secondary slot recognition area for the target view is generated based on the proportional positioning distribution of all target feature labels in all historical target views, and a corresponding secondary image slot is established at the primary image slot.

[0134] See also Figure 3 The above-mentioned first-level image slot refers to the slot corresponding to the device image in the view, such as the slot corresponding to the front view image, the slot corresponding to the top view image, etc.; the above-mentioned second-level image slot refers to the slot of a local area in the view.

[0135] S23, the first warehousing end interacts with the information extraction template based on the information extraction identifier to extract information from the warehousing target.

[0136] The first warehousing end of this solution can extract the required data of the warehoused items by combining the information extraction identifier and the information extraction template.

[0137] On the basis of the above embodiment, the information extraction template with information extraction identifier is generated based on the type information and quantity information of the sub-strategy in the warehousing strategy, and fed back to the first warehousing end, including:

[0138] If it is determined that the warehousing strategy includes a voice extraction sub-strategy and / or a text extraction sub-strategy, a first type slot corresponding to the voice extraction sub-strategy and / or the text extraction sub-strategy is established in the information extraction template, and the first type slot is a required slot. It can be understood that in this embodiment, when there is a voice extraction demand and / or a text extraction demand, it is necessary to generate corresponding first type slots on the information extraction template, including first type slots corresponding to voice and / or first type slots corresponding to text. The corresponding type of data can be filled in the first type slots later. Among them, the voice-related data can be, for example, the transportation data input by the first warehousing end, and the text-related data can be, for example, the time data input by the first warehousing end.

[0139] If it is determined that there is a secondary slot identification area, a second type slot corresponding to the secondary slot identification area is established for the voice extraction sub-strategy and / or the text extraction sub-strategy, and the second type slot is an optional slot. It is understandable that this solution will also establish a corresponding second type slot in the secondary slot identification area for the warehousing personnel to add notes data to the content corresponding to the secondary slot area. Among them, the second type slot is an optional slot, which means that the warehousing personnel can choose not to add the corresponding data.

[0140] S3, the multi-dimensional data model generates a corresponding interaction path based on the interaction method corresponding to the warehousing demand, the interaction starting point in the interaction path corresponds to the first warehousing end, and the other interaction nodes in the interaction path correspond to other warehousing management ends. It can be understood that the starting point of the interaction path corresponds to the first warehousing end, and the other interaction nodes on the path correspond to other warehousing management ends, that is, one interaction path may correspond to multiple warehousing ends.

[0141] In some embodiments, the multidimensional data model generates a corresponding interaction path based on the interaction method corresponding to the warehousing demand, the interaction starting point in the interaction path corresponds to the first warehousing end, and other interaction nodes in the interaction path correspond to other warehousing management ends, including:

[0142] S31, the multi-dimensional data model generates a corresponding interaction path based on the interaction method corresponding to the warehousing demand, and each warehousing demand has a preset interaction path.

[0143] It is worth mentioning that different devices have different equipment values, and different personnel are required to enter the warehouse. For example, device A requires personnel 1-personnel 3-personnel 4 to enter the warehouse, and device B requires personnel 2-personnel 3-personnel 5 to enter the warehouse. Therefore, there will be different interaction paths.

[0144] S32, sending the information extraction template to other warehousing management terminals, which add corresponding voice extraction sub-strategies and / or text extraction sub-strategies to the information extraction template, and set the voice extraction sub-strategies and / or text extraction sub-strategies corresponding to the generated proportional positioning area.

[0145] If other warehousing management terminals need to add voice or text information, they can add corresponding voice extraction sub-strategies and / or text extraction sub-strategies to the information extraction template, and then set them corresponding to the corresponding areas. The required remarks information can be added later.

[0146] S4, after determining that the multi-dimensional data model has received the storage data extracted by the first storage end and the interactive data fed back by the storage management end, it feeds back the corresponding storage demand to the server so that the server can complete the storage record.

[0147] As a key information processing and judgment center, the multidimensional data model connects the first warehousing end, the warehousing management end and the server, creating a seamless data link to ensure the accuracy and efficiency of the warehousing process. In this way, the multidimensional data model is effectively applied as an information integration and decision support tool in intelligent logistics and warehouse management systems. This improves the automation level of the warehousing process, reduces human errors, speeds up the overall warehousing process, and provides real-time and accurate inventory management.

[0148] See also Figure 4 , is a structural diagram of a goods warehousing interactive system applicable to a multi-dimensional data model provided by an embodiment of the present invention, including:

[0149] A judgment module, configured to enable the server to send the warehousing demand to the multidimensional data model when judging that the server has received the warehousing demand from the first warehousing end, wherein the multidimensional data model has a pre-configured warehousing strategy and an interaction method, and the warehousing strategy includes at least one of an image extraction sub-strategy, a voice extraction sub-strategy and / or a text extraction sub-strategy;

[0150] An analysis module is used to enable the multi-dimensional data model to analyze the warehousing demand, determine the corresponding warehousing strategy and feed it back to the corresponding first warehousing end, so that the first warehousing end extracts information about the warehousing target according to the warehousing strategy;

[0151] A generation module, configured to enable the multi-dimensional data model to generate a corresponding interaction path based on the interaction method corresponding to the warehousing demand, wherein the interaction starting point in the interaction path corresponds to the first warehousing end, and other interaction nodes in the interaction path correspond to other warehousing management ends;

[0152] The extraction module is used to enable the multi-dimensional data model to feed back the corresponding warehousing demand to the server after judging that it has received the warehousing data extracted by the first warehousing end and the interactive data fed back by the warehousing management end so that the server can complete the warehousing record.

[0153] The present invention also provides a storage medium, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the methods provided by the various embodiments described above.

[0154] Among them, the storage medium can be a computer storage medium or a communication medium. The communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The computer storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer. For example, the storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application-specific integrated circuit (Application Specific Integrated Circuits, referred to as ASIC). In addition, the ASIC can be located in a user device. Of course, the processor and the storage medium can also exist in a communication device as discrete components. The storage medium can be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0155] The present invention also provides a program product, which includes an execution instruction, which is stored in a storage medium. At least one processor of a device can read the execution instruction from the storage medium, and at least one processor executes the execution instruction so that the device implements the methods provided in the above various embodiments.

[0156] In the above-mentioned terminal or server embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0157] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A goods warehousing interaction method applicable to a multi-dimensional data model, characterized in that: include: When the server determines that it has received the warehousing demand from the first warehousing end, it sends the warehousing demand to the multidimensional data model, wherein the multidimensional data model has a pre-configured warehousing strategy and interaction method, and the warehousing strategy includes at least one of an image extraction sub-strategy, a voice extraction sub-strategy and / or a text extraction sub-strategy; The multi-dimensional data model analyzes the warehousing demand, determines a customized warehousing strategy and feeds it back to the corresponding first warehousing end, so that the first warehousing end extracts information about the warehousing target according to the warehousing strategy; The multi-dimensional data model extracts the entry strategy of the entry item labels; If it is determined that the warehousing strategy includes an image extraction sub-strategy, the image sub-model in the multi-dimensional data model obtains the warehousing category corresponding to the warehousing item label, and analyzes and processes the historical data of the warehousing category to obtain the historical image extraction features corresponding to the warehousing category; Acquire a feature label corresponding to each historical image extraction feature, and filter and process the feature label to obtain a target feature label, wherein the feature label at least includes a view label and a loss label; The image sub-model extracts a target view label and a target loss label corresponding to the target feature label, and establishes a corresponding image slot in the information extraction template based on the target view label and the target loss label; The first storage end interacts with the information extraction template based on the information extraction identifier to extract information from the storage target; The multidimensional data model generates a corresponding interaction path based on the interaction method corresponding to the warehousing demand, wherein the interaction starting point in the interaction path corresponds to the first warehousing end, and other interaction nodes in the interaction path correspond to other warehousing management ends; After determining that the multi-dimensional data model has received the storage data extracted by the first storage end and the interactive data fed back by the storage management end, the multi-dimensional data model feeds back the corresponding storage demand to the server so that the server completes the storage record.

2. The interactive method for goods warehousing applicable to a multi-dimensional data model according to claim 1, characterized in that: When the server determines that it has received the warehousing demand from the first warehousing end, it sends the warehousing demand to the multi-dimensional data model, and the multi-dimensional data model has a pre-configured warehousing strategy and interaction method, including: When the server determines that it has received the warehousing demand from the first warehousing end, it extracts the warehousing item label corresponding to the warehousing demand and sends it to the multi-dimensional data model; The multi-dimensional data model determines corresponding storage strategies and interaction methods based on the storage item labels, and each storage item label has a preset storage strategy and interaction method.

3. The interactive method for goods warehousing applicable to a multi-dimensional data model according to claim 2, characterized in that: The step of obtaining a feature label corresponding to each historical image extraction feature, filtering and processing the feature label to obtain a target feature label, wherein the feature label at least includes a view label and a loss label, comprises: Count the number of abnormal wear labels in each view label among all historical image extraction features of the same type of warehoused item labels, and count the number of normal wear labels in each view label; Generating a loss weight of each loss label based on the description information of the loss label, each description information having a preset loss weight; A calculation is performed based on the abnormal number, the normal number and the loss weight to obtain a feature label coefficient corresponding to the historical image extraction feature, and a target feature label is determined from multiple feature labels based on the feature label coefficient.

4. The interactive method for goods warehousing applicable to a multi-dimensional data model according to claim 3, characterized in that: The calculation based on the abnormal number, the normal number and the loss weight is performed to obtain a feature label coefficient corresponding to the historical image extraction feature, and a target feature label is determined from multiple feature labels based on the feature label coefficient, including: Adding the abnormal number to the normal number to obtain the total number, performing ratio calculation based on the abnormal number and the total number to obtain the abnormal ratio, and performing calculation based on the abnormal ratio, the preset ratio, and the preset number to obtain the calculated number; Obtain the loss weight of the loss label corresponding to each view label, and add the loss weights of the loss labels corresponding to the same type of view labels to obtain the average loss weight; Based on the average loss weight and the number of abnormal loss labels corresponding to each type of view label, a feature label coefficient of the corresponding type is calculated; A target feature label is determined from among a plurality of feature labels based on the calculation quantity and the feature label coefficient.

5. The interactive method for goods warehousing applicable to a multi-dimensional data model according to claim 4, characterized in that: The step of determining a target feature tag from a plurality of feature tags based on the calculated quantity and the feature tag coefficients includes: Sorting the plurality of feature labels in descending order based on the feature label coefficients to obtain a corresponding descending sorting sequence; According to the calculated quantity, the feature labels of the calculated quantity are sequentially traversed in the descending sort sequence to be selected as the determined target feature labels; The calculation quantity, average loss weight and feature label coefficient are obtained through the following formula: in, To calculate the quantity, is abnormal quantity, normal quantity For normal quantity, is a preset constant value, For the preset ratio, is the preset quantity, For the Types of feature label coefficients, For the Type The loss weight corresponding to the feature label, For the The upper limit of the number of features extracted from historical images corresponding to the feature labels in the first type is The number of features extracted from historical images corresponding to the feature labels in each type, For the The number of abnormal wear labels corresponding to the characteristic labels in the type, is the normalized value of quantity.

6. The interactive method for goods warehousing applicable to a multi-dimensional data model according to claim 5, characterized in that: The image sub-model extracts a target view label and a target loss label corresponding to the target feature label, and establishes a corresponding image slot in the information extraction template based on the target view label and the target loss label, including: The image sub-model extracts a target view label and a target loss label corresponding to the target feature label, wherein the target loss label has a view loss position corresponding to the target view; Proportionally positioning the loss position of the target view corresponding to the target view label based on the view loss position; A primary image slot corresponding to the target view is established at the information extraction template, and a secondary slot recognition area for the target view is generated based on the proportional positioning distribution of all target feature labels in all historical target views, and a corresponding secondary image slot is established at the primary image slot.

7. The interactive method for goods warehousing applicable to a multi-dimensional data model according to claim 6, characterized in that: The proportionally positioning the loss position of the target view corresponding to the target view label based on the view loss position includes: Acquire a loss view corresponding to the view loss position, perform coordinate processing on the target view according to a preset point as the origin, and acquire the corner point coordinates of a preset corner point of the target view; Extracting the first X-axis value and the first Y-axis value corresponding to the corner point coordinates to generate the corresponding first X-axis interval value and the first Y-axis interval value; Acquire the second X-axis value and the second Y-axis value in the loss view to generate corresponding second X-axis interval value and second Y-axis interval value; Proportional positioning of the X-axis is performed based on the first X-axis interval value and the second X-axis interval, and proportional positioning of the Y-axis is performed based on the first Y-axis interval value and the second Y-axis interval.

8. The interactive method for goods warehousing applicable to a multi-dimensional data model according to claim 7, characterized in that: The extracting the corresponding first X-axis value and the first Y-axis value from the corner point coordinates to generate the corresponding first X-axis interval value and the first Y-axis interval value includes: Extracting the largest first X-axis value and the smallest first X-axis value in the corner point coordinates to obtain corresponding first X-axis interval values; Extracting the largest first Y-axis value and the smallest first Y-axis value in the corner point coordinates to obtain corresponding first Y-axis interval values; The step of acquiring the second X-axis value and the second Y-axis value in the loss view to generate corresponding second X-axis interval value and second Y-axis interval value comprises: Extract the maximum second X-axis value and the minimum second X-axis value in the loss view to obtain the corresponding second X-axis interval value; Extract the maximum second Y-axis value and the minimum second Y-axis value in the loss view to obtain the corresponding second Y-axis interval value; The performing proportional positioning of the X-axis based on the first X-axis interval value and the second X-axis interval, and the performing proportional positioning of the Y-axis based on the first Y-axis interval value and the second Y-axis interval, comprises: Determine the X-axis segments of the second X-axis interval that overlap with the values ​​of the first X-axis interval, and determine the Y-axis segments of the second Y-axis interval that overlap with the values ​​of the first Y-axis interval; Proportional positioning is performed on the loss position of the target view according to the overlapping X-axis segments and the overlapping Y-axis segments, and the proportional positioning area is highlighted.

9. A goods warehousing interactive system applicable to a multi-dimensional data model, characterized in that: include: A judgment module, configured to enable the server to send the warehousing demand to the multidimensional data model when judging that the server has received the warehousing demand from the first warehousing end, wherein the multidimensional data model has a pre-configured warehousing strategy and an interaction method, and the warehousing strategy includes at least one of an image extraction sub-strategy, a voice extraction sub-strategy and / or a text extraction sub-strategy; An analysis module is used to enable the multi-dimensional data model to analyze the warehousing demand, determine the corresponding warehousing strategy and feed it back to the corresponding first warehousing end, so that the first warehousing end extracts information about the warehousing target according to the warehousing strategy; The multi-dimensional data model extracts the storage strategy of the storage item labels; If it is determined that the warehousing strategy includes an image extraction sub-strategy, the image sub-model in the multi-dimensional data model obtains the warehousing category corresponding to the warehousing item label, and analyzes and processes the historical data of the warehousing category to obtain the historical image extraction features corresponding to the warehousing category; Acquire a feature label corresponding to each historical image extraction feature, and filter and process the feature label to obtain a target feature label, wherein the feature label at least includes a view label and a loss label; The image sub-model extracts a target view label and a target loss label corresponding to the target feature label, and establishes a corresponding image slot in the information extraction template based on the target view label and the target loss label; The first storage end interacts with the information extraction template based on the information extraction identifier to extract information from the storage target; A generation module, configured to enable the multi-dimensional data model to generate a corresponding interaction path based on the interaction method corresponding to the warehousing demand, wherein the interaction starting point in the interaction path corresponds to the first warehousing end, and other interaction nodes in the interaction path correspond to other warehousing management ends; The extraction module is used to enable the multi-dimensional data model to feed back the corresponding warehousing demand to the server after judging that it has received the warehousing data extracted by the first warehousing end and the interactive data fed back by the warehousing management end so that the server can complete the warehousing record.

Images