A product data real-time monitoring and analyzing method based on commodity bar code

Abstract

The application discloses a product data real-time monitoring and analyzing method based on commodity bar codes, which supervises the risks that the target product in the sales end storage may face based on the weather conditions. If a factor that may cause risks to the storage environment appears before the target product is delivered, an alarm is sent to the sales end to prompt the sales end to process the target product, so that further losses caused by the blind flow into the market are avoided. Moreover, the method in the application adopts sales codes instead of preset codes when supervising the target product, so that even if an attacker wants to tamper with the sales records of the target product to divert the target product with risks, the management end can also be aware of it, which is beneficial to risk management. It can be seen that the method provided by the application can realize product data real-time monitoring and analyzing based on commodity bar codes by using data processing technologies for management, supervision or prediction purposes.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data processing technology for management, supervision or prediction purposes, and in particular to a product data real-time monitoring analysis method based on commodity barcodes. BACKGROUND

[0002] With the improvement of the quality of life, people's requirements for product quality have also changed. Factors affecting product quality are not only the production process, but also the transportation process of the product and the storage process at the sales end. Especially for products such as medicines, baby products, which have relatively strict requirements on storage conditions, if there is a problem in the middle link, it is likely to affect the quality of the product. If the product with quality problems is sold to the user, it will likely cause harm. Moreover, the value of these products is also relatively high, and the loss caused by the damage of their quality is multifaceted.

[0003] It can be seen that how to provide a product implementation monitoring method is a problem to be solved.

[0004] For example, publication (announcement) number: CN102930369A, patent title: "a barcoding management method for product manufacturing process" (main classification number: G06Q10 / 06), by converting the products to be managed and all production elements through barcodes to distinguish them, scanning the products and production elements through barcodes to store them into a computer database for saving, realizing the digitization of product management.

[0005] On the one hand, it can be shown that data processing technology for management, supervision or prediction purposes has great potential in the field of product quality supervision related technology; on the other hand, it can also be shown that there is a relatively wide expansion prospect for the technical mining in this field. SUMMARY

[0006] The embodiments of the present application provide a product data real-time monitoring analysis method based on commodity barcodes to at least partially solve the above technical problems.

[0007] The embodiments of the present application adopt the following technical solutions:

[0008] In a first aspect, the embodiments of the present application provide a product data real-time monitoring analysis method based on commodity barcodes, which is based on a monitoring system, the monitoring system including a management end and a sales end; the method comprises:

[0009] The management end acquires the predicted meteorological data of the transportation path planned for the target product when detecting the factory shipment of the target product;

[0010] When the target product reaches the sales end, a first coefficient is determined based on a transportation risk coefficient and a preset storage risk level of the sales end, and is added to a preset code of the target product to generate a sales code, which is stored locally; the transportation risk coefficient represents a degree to which a transportation operation in the transportation path is affected by a meteorological condition represented by the predicted meteorological data;

[0011] When it is detected that the sales end scans the preset code of the target product for storage, a sales code corresponding to the preset code is sent to the sales end, so that the sales end updates the preset code with the sales code and stores it locally;

[0012] Actual meteorological data of a location of the sales end is received, and when it is detected that a second coefficient is greater than a preset second coefficient threshold, it is determined whether the target product is stored based on the sales code; the second coefficient is obtained based on the storage risk level and the actual meteorological data, and represents a degree to which the target product is affected by a natural disaster in a storage process;

[0013] If the target product is not stored, a storage warning information is sent to the sales end.

[0014] In an optional embodiment of the present specification, the method further comprises:

[0015] If it is determined that the target product is not stored based on the sales code, it is determined whether the target product is stored based on the preset code;

[0016] If the target product is not stored, the storage warning information is sent to the sales end.

[0017] In an optional embodiment of the present specification, the method further comprises:

[0018] If it is determined that the target product is stored based on the preset code, a theft warning information is sent to the sales end.

[0019] In an optional embodiment of the present specification, determining the first coefficient comprises:

[0020] The transportation risk coefficient is determined based on a driving condition of a vehicle carrying the target product on the transportation path; the transportation risk coefficient in a case where the driving condition indicates that a transportation efficiency of the vehicle does not meet an expectation and the predicted meteorological data indicates that there is a traffic hazard on the transportation path is greater than the transportation risk coefficient in a case where the driving condition indicates that the transportation efficiency of the vehicle meets the expectation and the predicted meteorological data indicates that there is no traffic hazard on the transportation path;

[0021] constructing a usable field based on the transportation risk coefficient, the storage risk level, and the serial number of the target product;

[0022] processing the usable field by using a hash algorithm to obtain the first coefficient.

[0023] In an optional embodiment of the present specification, the monitoring system further comprises a supervision end, and the method further comprises:

[0024] sending the storage alarm information and / or the theft alarm information to the supervision end;

[0025] canceling the alarm after receiving the receipt of the supervision end.

[0026] In an optional embodiment of the present specification, the method further comprises:

[0027] when detecting that the target product is stored, determining a focus time period for the target product based on the validity period of the target product and the storage risk level, and starting timing; the length of the focus time period is less than or equal to the validity period of the target product;

[0028] when the focus time period ends, sending product validity alarm information to the sales end.

[0029] In an optional embodiment of the present specification, the method further comprises:

[0030] The focus time period is obtained by using a pre-trained first support vector machine model; and the first support vector machine model is trained by using historical data.

[0031] In an optional embodiment of the present specification, the method further comprises:

[0032] based on historical event data, constructing a sample and a label corresponding to the sample; the sample represents information represented by a preset encoding table of a historical product involved in a historical event to which the sample belongs, a storage risk level of a sales end storing the historical product, and natural disaster data involved in the historical event; and the label represents an influence degree of the historical event on the historical product in a natural disaster in a storage process;

[0033] training a preset support vector machine model by using the sample and the label to obtain a second support vector machine model;

[0034] when receiving actual meteorological data of a location of the sales end, determining the second coefficient by using the second support vector machine model.

[0035] In an optional embodiment of the present specification, the method further comprises:

[0036] In a case where the storage risk level is greater than a preset level threshold, a third coefficient of the target product is determined when it is detected that the target product is delivered; the third coefficient represents a combination of respective second coefficients at respective historical time nodes in the storage process of the target product; the historical time nodes are time nodes at which meteorological events have occurred in history;

[0037] If the third coefficient is greater than a preset third coefficient threshold, a confirmation alarm information is sent to the sales end.

[0038] In an optional embodiment of the present specification, the method further comprises:

[0039] If the receipt for the storage alarm information indicates that the target product has a quality risk, the target product is determined as a reference product;

[0040] Based on the preset encoding, a risk product is found from the alternative products, which has a similarity greater than a preset similarity first threshold with the reference product, and a predicted meteorological data of a location of a sales end to which the risk product belongs has a similarity greater than a preset similarity second threshold with an actual meteorological data of a location of a sales end to which the reference product belongs.

[0041] An inspection alarm information is sent to the sales end to which the risk product belongs.

[0042] In a second aspect, the embodiments of the present application further provide a product data real-time monitoring and analysis device based on a commodity bar code, which is used to implement the method steps in the first aspect.

[0043] In a third aspect, the embodiments of the present application further provide an electronic device, which comprises:

[0044] a processor; and

[0045] a memory arranged to store computer executable instructions, which, when executed, cause the processor to perform the method steps in the first aspect.

[0046] In a fourth aspect, the embodiments of the present application further provide a computer readable storage medium, which stores one or more programs, which, when executed by an electronic device comprising a plurality of application programs, cause the electronic device to perform the method steps in the first aspect.

[0047] The above at least one technical solution adopted by the embodiments of the present application can achieve the following beneficial effects:

[0048] The method provided by the application can supervise the risk that the target product in the sales end warehouse may face based on the weather condition by the management end. If a factor that may cause risk to the warehouse environment appears before the target product is delivered, an alarm is sent to the sales end to prompt the sales end to process the target product to avoid further loss caused by blind flow into the market. Moreover, the method in the application uses sales code instead of preset code when supervising the target product. The sales code is known only by the management end and the legal sales end, and other ends cannot know it. This makes it possible for the attacker to tamper with the sales record of the target product to divert the target product with risk, which will be detected by the management end, which is beneficial to realize risk management. It can be seen that the method provided by the application can realize real-time monitoring and analysis of product data based on commodity bar code by using data processing technology for management, supervision or prediction. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1 A process schematic diagram of a product data real-time monitoring and analysis method based on commodity bar code provided by an embodiment of the present application;

[0050] Figure 2 A structural schematic diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0051] The application will be further described in detail through specific embodiments in combination with the drawings. In different embodiments, similar elements are associated with similar element labels. In the following embodiments, many details are described in order to make the application better understood. However, those skilled in the art can easily recognize that some features can be omitted in different cases, or can be replaced by other elements, materials or methods. In some cases, some operations related to the application are not shown or described in the specification in order to avoid the core part of the application being overwhelmed by too much description, and it is not necessary to describe these related operations in detail for those skilled in the art according to the description in the specification and general technical knowledge in the art.

[0052] In addition, the features, operations or characteristics described in the specification can be combined in any appropriate way to form various embodiments. At the same time, the steps or actions in the method description can also be sequentially changed or adjusted in a manner that is obvious to those skilled in the art. Therefore, the order in the specification and the drawings is only for clear description of a certain embodiment, and does not mean a necessary order, unless otherwise stated that a certain order must be followed.

[0053] The serial numbers of components in this paper, such as "first", "second", etc., are only used to distinguish the described objects, and have no technical meaning. Unless otherwise specified, "connection" and "coupling" in this application include direct and indirect connections (couplings).

[0054] The technical solutions provided by the embodiments of the application will be described in detail below with reference to the drawings.

[0055] The method in the specification is based on a monitoring system, which includes a management end and a sales end. They are communicatively connected. The management end can be a distributed server, and the sales end can be an address including a terminal device. The terminal device has a code scanning function. Unless otherwise specified, the execution subject of the method in the specification is the management end. The sales end in the specification can not be unique, and the specification only takes one of them as an example for description.

[0056] In the system architecture, data transmission between the management end and other ends can use two types of standardized protocol schemes:

[0057] 1. HTTP / HTTPS secure transmission protocol.

[0058] As a secure enhanced version of HTTP, HTTPS realizes the following core features through the SSL / TLS encryption layer: two-way identity verification: the server needs to submit a CA authenticated digital certificate, and the client verifies the identity authenticity through the public key infrastructure (PKI). Hybrid encryption system: asymmetric encryption (RSA / ECC algorithm): used in the key negotiation phase, public key encryption request data, and private key decryption to ensure initial security. Symmetric encryption (AES algorithm): after establishing a session key, high-efficiency symmetric encryption is used to process business data streams. Protocol evolution optimization: HTTP / 1.1 introduces a connection multiplexing mechanism to reduce latency. HTTP / 2 uses binary framing and header compression technology to improve throughput by more than 50%.

[0059] 2. MQTT Internet of Things message protocol.

[0060] This ISO standard protocol (ISO / IEC 20922) is based on the publish / subscribe mode and has the following design advantages: simple protocol header: 2-byte fixed header + variable payload, with a minimum of only 4 bytes per data packet, especially suitable for narrowband scenarios such as NB-IoT. Loose coupling architecture: message broker (Broker) decouples direct dependencies between devices. Support for topic (Topic) hierarchical routing (such as factory / device1 / temperature). Fault tolerance mechanism: Last Will and Testament (LWT) triggers an alarm when the connection is abnormally disconnected. Persistent session preserves subscription relationships and unconfirmed messages.

[0061] For example, Figure 1As shown, the product data real-time monitoring analysis method based on commodity barcodes in the specification comprises the following steps:

[0062] S100: When detecting that the target product is shipped, the management end obtains the predicted meteorological data of the transportation path planned for the target product.

[0063] The type of target product in the specification is not limited, and all products in the related art can be used as the target product in the specification under the condition that the condition is allowed. Some products, such as medicines and baby products, may cause great harm when their quality is at risk, so the method in the specification can play a more strict supervisory and management role. The target product in the specification can not be unique, and the serial number in the GS1 code of different target products is different. The specification only takes one of the target products as an example for description.

[0064] The transportation path is the path from the production place of the product to the sales place (the place of the sales end), and the technical means for path planning in the related art is applicable to the specification under the condition that the condition is allowed. The predicted meteorological data can be obtained from the related meteorological data segment.

[0065] It should be noted that in long-distance transportation operations, there may also be situations that require updating of predicted meteorological data, which is also allowed in the technical solution of the specification.

[0066] S102: When the target product arrives at the sales end, based on the transportation risk coefficient and the storage risk level preset by the sales end, a first coefficient is determined and added to the preset code of the target product to generate a sales code and store it locally.

[0067] The management end can obtain the positioning information of the target product from the vehicle transporting the target product, and then determine whether the target product has arrived at the sales end.

[0068] Different sales terminals provide different storage conditions for the target product, resulting in different storage risk levels. The higher the storage risk level, the less favorable the storage of the target product, and the greater the risk of causing quality risks to the target product. In related technologies, the technical means capable of quantifying the storage conditions are applicable to the present specification under the condition of permission. For example, the storage condition of providing refrigeration for the target product will reduce the storage risk level; the sales terminal has not experienced flood disasters in history, which will reduce the storage risk level; the higher the latitude of the sales terminal, the lower the storage risk level. There are other factors that affect the storage risk level, which can be selected according to the actual situation. The storage risk level can be a value between 0 and 1, and the higher the value, the higher the risk. The storage risk level is quantified according to the unified standard by the management terminal in combination with the data representing the storage conditions fed back by the sales terminal, and the process can also be combined with artificial experience.

[0069] It can be understood that the sales terminal will formulate the storage condition for the target product according to its own situation, and it is difficult to achieve uniformity among different sales terminals.

[0070] The transportation risk coefficient in the present specification represents the degree to which the transportation operation in the transportation path is affected by the predicted meteorological data. In an optional embodiment of the present specification, the transportation risk coefficient is determined based on the driving condition of the vehicle carrying the target product on the transportation path. In the case where the driving condition indicates that the transportation efficiency of the vehicle does not meet the expectation, and the predicted meteorological data indicates that there is a traffic hazard on the transportation path (indicating that the transportation is likely to be indeed affected by the weather, for example, heavy rain causes road interruption, and the target product on the vehicle may also be wet or soaked), the transportation risk coefficient is greater than that in the case where the driving condition indicates that the transportation efficiency of the vehicle meets the expectation, and the predicted meteorological data indicates that there is no traffic hazard on the transportation path.

[0071] The transportation risk coefficient in the case where the transportation efficiency of the vehicle meets the expectation, and the predicted meteorological data indicates that there is a traffic hazard on the transportation path, is less than that in the case where the transportation efficiency of the vehicle does not meet the expectation, and the predicted meteorological data indicates that there is a traffic hazard on the transportation path.

[0072] The transportation risk coefficient in the case where the transportation efficiency of the vehicle does not meet the expectation, and the predicted meteorological data indicates that there is no traffic hazard on the transportation path, is the same as that in the case where the transportation efficiency of the vehicle meets the expectation, and the predicted meteorological data indicates that there is no traffic hazard on the transportation path.

[0073] In the related art, the technical means that can realize the quantization process of the transportation risk coefficient are all applicable to the present specification under the condition that the conditions allow. The transportation risk coefficient can be a number before 0 to 1.

[0074] In a further optional embodiment of the present specification, before determining the first coefficient, it is first determined whether the transportation risk coefficient is greater than a preset transportation risk threshold value (empirical value). If yes, it indicates that the quality of the target product is affected during the transportation process, and a transportation warning is issued to the sales end and the regulatory end mentioned below, so as to timely determine whether the batch of target products needs to be quarantined to avoid flowing into the market or to be processed. If no, the first coefficient is determined based on the transportation risk coefficient. Specifically, based on the transportation risk coefficient, the storage risk level, and the serial number of the target product (read from the preset code), a usable field is constructed (for example, arranging the three in a preset order, that is, obtaining the usable field); the hash algorithm is used to process the usable field to obtain the first coefficient. The first coefficient obtained in this way is irreversible and cannot be known by the attacker before attacking the management end and the sales end, and has a certain encryption property. The sales code obtained on this basis also has the property of encryption, and even if the risk end scans the preset code on the target product, the sales code cannot be known, so that the outbound of the target product cannot be normally realized. If there is no outbound record, the destruction program will be started when the target product expires, and if the target product cannot be found at that time, the risk behavior will be exposed. If the outbound is carried out with the preset code, it indicates that the sales end is abnormal and may have been attacked, or the sales end itself is a risk, and the risk behavior can be immediately exposed, so that the management end can be aware.

[0075] The management end generates the first coefficient only when the target product arrives at the sales end, rather than generating the first coefficient in advance. On the one hand, the unpredictability of the situation during the transportation process leads to the unpredictability of the first coefficient, which further improves the encryption effect; on the other hand, it can also reduce the risk of leakage of the first coefficient.

[0076] The preset code and the sales code in the specification (i.e., the code that needs to be scanned when the target product is sold, the scanning of which by the technical means in the specification is a virtual scanning rather than scanning the mark) both belong to the GS1 code. The Global Trade Item Number (GTIN) is the most commonly used product identifier in the coding system described herein. As a core component of the GS1 business common language system, it can give any form of trade goods or services a unique digital identity. The coding system includes four specific structures: 13-bit, 14-bit, 8-bit, and 12-bit digital combinations (corresponding to GTIN-13 / 14 / 8 / 12, respectively) to meet the coding needs of various types of product packaging. It should be particularly emphasized that each GTIN code must be used as a complete unit to ensure its absolute uniqueness in global commercial circulation. This standardized identification system forms the cornerstone of the GS1 global unified coding system. The identification based on the GS1 in the specification can be a bar code or a two-dimensional code.

[0077] The preset code includes at least one of the following: batch number (GS1 code (10), representing product batch, defined by the manufacturer), serial number (GS1 code (21), representing unique sequence identifier, also known as "serial number"), consumer product variant (GS1 code (22), defined by the manufacturer), and relevant date (date-related information such as production date, etc.). The first coefficient can be added to the GS1 code (21) to express uniqueness.

[0078] S104: When detecting that the sales end scans the preset code of the target product into the warehouse, the sales code corresponding to the preset code is sent to the sales end.

[0079] When the sales end receives the sales code sent by the management end, the sales end updates the preset code with the sales code and stores it locally. Then, when the target product is delivered, the sales end will automatically find the sales code corresponding to the preset code on the packaging of the target product from the local and scan the sales code. The preset code can be set on the sales packaging of the target product and can be a bar code.

[0080] In an optional embodiment, the sales end scans the preset code on the target product when it is delivered into the warehouse and sends a data request to the management end. The management end returns the sales code including the first coefficient to the sales end, and also returns other information included in the sales code, such as product name, expiration date, etc., or rules for interpreting the code.

[0081] S106: Receive the actual meteorological data of the location of the sales end, and when detecting that the second coefficient is greater than the preset second coefficient threshold, determine whether the target product is delivered based on the sales code.

[0082] In the related art, the technical means capable of achieving the acquisition of actual meteorological data are all applicable to the present specification under the condition that the conditions are allowed. The actual meteorological data is historical data, which characterizes the meteorological situation that has occurred, and the risk caused thereby is also real. Whether the target product is out of stock can be realized through interaction with the sales end. The second coefficient threshold value can be an empirical value.

[0083] When the target product is out of stock, it will also be scanned. At this time, although the preset code is scanned, it has been updated, and in an ideal case, the object scanned at the time of out of stock is the sales code. The scanning of the sales code will leave a record in the system, which can be used to determine whether it is out of stock.

[0084] In actual application, the sales end connected by the management end is not unique, and the actual meteorological data of the sales end can be received in real time, and the judgment based on the second coefficient can be executed in real time to determine which sales end needs further processing.

[0085] If the target product has been out of stock, it indicates that even if there is a risk, the risk can be avoided, and it is not necessary to investigate.

[0086] The second coefficient in the present specification is obtained based on the warehouse risk level and the actual meteorological data, and characterizes the degree of influence of the target product by natural disasters in the warehouse process. The higher the second coefficient, the more obvious the influence of natural disasters on the target product at the sales end, and the higher the risk to the product quality.

[0087] In an optional embodiment of the present specification, the second coefficient can be determined based on artificial experience.

[0088] In another optional embodiment of the present specification, based on historical event data (historical events are events caused by meteorological reasons, such as floods, heat disasters, etc. These events may cause the products in storage to be affected), a sample and a label corresponding to the sample are constructed; the sample represents the information represented by the preset encoding table of the historical product involved in the historical event to which the sample belongs (these information can include category information, which distinguishes the category of the product, such as electronic products, pharmaceuticals, etc. It can also include the qualified rate of the batch in which the product is located, the test result, etc. It can also include the expiration date, the recommended storage condition, etc.), the storage risk level of the sales end where the historical product is stored, and the natural disaster data involved in the historical event (such as the amount of precipitation, etc.); the label represents the degree of influence (quantitative value can be between 0 and 1, the greater the value, the greater the negative impact) of the historical event on the natural disaster of the historical product in the storage process; the preset support vector machine model is trained using the sample and the label to obtain a second support vector machine model; when the actual meteorological data of the location of the sales end is received, the second support vector machine model is used to determine the second coefficient. The second support vector machine model in the present specification can learn the influence of various factors on the risk through training.

[0089] Support Vector Machine (SVM) as a supervised learning model, its design core embodies the natural law of mathematics and optimization field, as follows:

[0090] Maximum margin principle: the core goal of SVM is to construct an optimal hyperplane in high-dimensional space through convex optimization method, so that the minimum distance (i.e. margin) of positive and negative class samples to the hyperplane is maximized; this is derived from the distance optimization idea in geometry, which calculates the margin distance through vector dot product and projection calculation, to ensure that the decision boundary has the strongest generalization ability.

[0091] Kernel trick for non-linear processing: for linearly inseparable data, SVM introduces kernel function (such as linear kernel or Gaussian kernel), which maps the original data to high-dimensional feature space, so that the problem is transformed into linearly separable; this follows the mathematical law of dimension expansion, which implicitly calculates the high-dimensional inner product through kernel function, avoiding the computational overhead of explicit mapping.

[0092] Constraint optimization and regularization mechanism: to deal with noise or outliers, SVM combines slack variables and regularization parameter C to balance between classification error and margin size; the solution process needs to satisfy KKT conditions (such as gradient is zero and complementary relaxation), to ensure the uniqueness and global optimality of the solution.

[0093] Sparsity and structural risk minimization: the final decision boundary is determined only by support vectors (samples located on the margin boundary), which embodies the sparsity of the algorithm; this design is based on the principle of structural risk minimization, which improves the generalization ability by controlling the model complexity, and is especially suitable for small sample and high-dimensional data scenarios.

[0094] These laws together give SVM strong robustness and wide adaptability, and can be extended to multi-classification, regression and other tasks.

[0095] S108: If the target product is not out of the warehouse, the warehousing warning information is sent to the sales end.

[0096] The target product is not out of the warehouse, which means that the risk caused by the warehouse may affect the target product, and further measures need to be taken. The warehousing warning information is used to alert the sales end to carry out inspection on the target product, so as to more accurately judge whether its condition leads to quality hidden danger in an artificial way.

[0097] The method provided in the application supervises the risk that the target product in the sales end warehouse may face based on the weather condition by the management end. If a factor that may cause risk to the warehouse environment appears before the target product is out of the warehouse, an alarm is sent to the sales end to prompt the sales end to process the target product, so as to avoid further loss caused by blind flow into the market. Moreover, the method in the application uses sales code when supervising the target product, instead of preset code. The sales code is known only by the management end and the legal sales end, and other ends cannot know it. This makes even if an attacker wants to tamper with the sales record of the target product to divert the target product with risk, it will be detected by the management end, which is conducive to risk management. It can be seen that the method provided in the application can realize real-time monitoring and analysis of product data based on commodity bar code by using data processing technology for management, supervision or prediction purposes.

[0098] Moreover, the risks that the target product faces in reality are not only natural disasters, but also man-made illegal behaviors. Since the preset code and the sales code are both made according to preset enterprise rules, which are different from each other, the risk end cannot know the complete information of the target product even if it gets the target product, and can only obtain the information by scanning the code. The risk end does not store the sales code locally, and in fact can only scan the preset code, which provides more conditions for the management of the management end. In an optional embodiment of the present specification, if it is judged based on the sales code that the target product has not been out of the warehouse, it is judged based on the preset code whether the target product has been out of the warehouse; if the target product has not been out of the warehouse (indicating that the target product has not been obtained by the attacker), the warehouse alarm information is sent to the sales end. If it is judged based on the preset code that the target product has been out of the warehouse, the theft alarm information is sent to the sales end to inform the sales end that the target product may be at risk of being stolen.

[0099] In actual application, the detection of the preset code triggered based on the meteorological data is only one choice of detection timing, and in fact, the detection of the preset code can also be performed in real time to strengthen the prevention of the attacker.

[0100] In an optional embodiment of the present specification, the monitoring system further comprises a supervision end. The supervision end can be an independent third end, and can be an end with independent supervision functions, such as a public supervision department. In addition, the supervision end can also be the production end of the target product, or the upstream management department of the sales end, etc. The method in the present specification can further comprise: sending the warehouse alarm information and / or the theft alarm information to the supervision end, so that the management end verifies the target product. After receiving the receipt of the supervision end, the management end indicates that the management end has performed the corresponding processing, and then cancels the alarm.

[0101] Further, if the receipt for the warehouse alarm information indicates that the target product has a quality risk (e.g., water seeps into the packaging after being soaked, the product is damaged due to wind blowing down the shelf, etc. The receipt contains the preset code and / or the sales code of the target product), the target product is determined as a reference product. The management end finds, from the alternative products (each product has not been shipped out), a product that has a similarity greater than a preset similarity first threshold (the similarity first threshold can be an empirical value. For products of the same batch, only the serial number is different in the preset code. This step can be regarded as finding a target product of the same batch but different sales ends. Due to processes, raw materials, and equipment, there may be slight differences between different batches. For example, products of batch A use a packaging material a, which meets the corresponding standards but is prone to water seepage. Products of batch B use a packaging material b, which has better waterproof effect), and the prediction meteorological data of the sales end where the product belongs has a similarity greater than a preset similarity second threshold (the similarity second threshold can be an empirical value. The problems of the same batch under the same or similar meteorological conditions and warehouse conditions are usually similar. Even if the target product of the other sales end is not sufficient or has not yet reached the standard for making a judgment based on actual meteorological data, the potential risk cannot be ignored) to the actual meteorological data of the sales end where the reference product belongs, as a risk product. An inspection alarm information is sent to the sales end where the risk product belongs, so that the sales end takes preventive measures.

[0102] In actual product storage process, not only meteorological disasters, but also other factors can cause quality problems of products. For example, products under refrigeration conditions can have better storage effect than products without refrigeration conditions. In an optional embodiment of the present specification, meteorological conditions are not considered, only storage conditions are considered, and monitoring is realized based on storage conditions. In this embodiment, when the target product is detected to be stored, a concerned time period is determined for the target product based on the shelf life of the target product and the warehouse risk level, and timing starts; the length of the concerned time period is less than or equal to the shelf life of the target product; at the end of the concerned time period, a product validity alarm information is sent to the sales end, so that the sales end inspects the product. In some cases, the quality of the product changes obviously, for example, the bag swells; in some cases, more professional means are needed.

[0103] The concerned time period is a time period under the storage condition, within the shelf life, and capable of ensuring the quality of the product. For example, the shelf life of a certain milk powder is 6 months, and it is recommended to be stored at 8 degrees Celsius. However, due to equipment problems, the actual storage condition can only be guaranteed at 6 degrees Celsius to 10 degrees Celsius. Although it also meets the storage condition, it may cause the concerned time period to be 4 months.

[0104] Since the support vector machine can also be trained as a regression model, as a statistical analysis tool, it is used to establish a quantitative relationship model between variables, help to predict future values, explain causal relationships, and provide data support for decision-making. Therefore, in an optional embodiment of the present specification, the period of interest is obtained by using a pre-trained first support vector machine model; the first support vector machine model is trained using historical data. The historical data shows the time when the product quality of different types of products under different warehouse risk levels appears to be at risk, so as to represent how long the corresponding period of interest is. The historical data can be obtained from the sales end in history. For example, milk powder C (with preset coded information representing the qualified rate of the batch it belongs to, test results, etc.) under the storage conditions of sales end D originally has a shelf life of 6 months, but it has deteriorated after 4 months. The type of deterioration is caking, and the degree of deterioration is slight (which can be represented by a quantified value, for example, between 0 and 1, 1 for complete failure condition serious), but it is not recommended to eat, and the data is provided by the buyer customer.

[0105] In a further optional embodiment of the present specification, if the meteorological conditions are also considered, and the meteorological conditions are not bad enough to trigger the judgment based on the second coefficient threshold, then in the case where the warehouse risk level is greater than a preset level threshold (an empirical value related to the loss caused by the failure of the target product), the third coefficient of the target product can be determined when the target product is detected to be out of the warehouse. The third coefficient represents the comprehensive (the comprehensive method can be various, such as mean or median) of the respective second coefficients at each historical time node in the storage process of the target product; the historical time node is the time node at which a meteorological event (such as high temperature, heavy rain, high humidity, etc.) occurred in history, but these events are not enough to trigger the judgment based on the second coefficient threshold.

[0106] If the third coefficient is greater than a preset third coefficient threshold (an empirical value, and greater than the second coefficient threshold), and the number of historical time nodes is greater than a preset number threshold (an empirical value), an alarm information is sent to the sales end to make the sales end perform an inspection on the target product, and then determine whether it can be out of the warehouse.

[0107] Further, the present specification also provides a product data real-time monitoring and analysis device based on commodity bar code, which is used to implement the method steps described above.

[0108] The device can perform the method in any of the preceding embodiments and can obtain the same or similar technical effects, which will not be described here again.

[0109] Figure 2 is a structural schematic diagram of an electronic device according to an embodiment of the present application. Please refer to Figure 2At the hardware level, the electronic device comprises a processor, and optionally further comprises an internal bus, a network interface, and a memory. The memory can include a memory such as a random-access memory (RAM), and can further include a non-volatile memory such as at least one disk memory. Of course, the electronic device can further include other hardware required by the business.

[0110] The processor, the network interface, and the memory can be connected to each other through the internal bus, which can be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, and a control bus, etc. For ease of representation, Figure 2 Only one bidirectional arrow is used to represent the internal bus in the figure, but it does not mean that there is only one bus or only one type of bus.

[0111] The memory is used to store a program. Specifically, the program can include program code including computer operation instructions. The memory can include a memory and a non-volatile memory, and provide instructions and data to the processor.

[0112] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs, and forms a product data real-time monitoring and analysis device based on a commodity barcode at the logical level. The processor executes the program stored in the memory, and is specifically configured to execute any one of the product data real-time monitoring and analysis methods based on a commodity barcode.

[0113] The above as described in the present application Figure 1The product data real-time monitoring and analysis method based on commodity bar code disclosed by the embodiment can be applied to a processor or implemented by the processor. The processor can be an integrated circuit chip with signal processing capability. In the implementation, the steps of the method can be completed by integrated logic circuits of hardware in the processor or instructions in the form of software. The processor can be a general processor, including a central processing unit (CPU), a network processor (NP), etc. It can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware code processor for execution, or a combination of hardware and software modules in the code processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. The storage medium in the storage, the processor reads the information in the storage, and combines the hardware to complete the steps of the method.

[0114] The electronic device can also execute Figure 1 a product data real-time monitoring and analysis method based on commodity bar code, and implement Figure 1 the functions of the embodiment, which will not be described here.

[0115] The embodiment of the present application also proposes a computer readable storage medium, which stores one or more programs, the one or more programs including instructions, the instructions being executed by an electronic device including a plurality of application programs to execute any one of the aforementioned product data real-time monitoring and analysis methods based on commodity bar code.

[0116] Those skilled in the art will appreciate that embodiments of the present application can be readily used as software, hardware, or a combination of software and hardware. In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0117] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks.

[0118] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks.

[0119] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks.

[0120] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0121] The memory can include non-persistent memory and / or persistent memory, such as flash memory, or a readonly memory (ROM). The memory is an example of computer readable media.

[0122] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0123] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusions, such that a process, method, article or apparatus that comprises a list of elements does not only include those elements, but also other elements not explicitly listed, or other elements inherent to such a process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0124] Those skilled in the art will appreciate that embodiments of the present application can be provided as methods, systems or computer program products. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) containing computer usable program code.

[0125] The above only describes the embodiments of the present application and is not intended to limit the present application. Those skilled in the art can make various changes and modifications to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the scope of the claims of the present application.

Claims

1. A method for real-time monitoring and analysis of product data based on commodity barcodes, characterized in that, The method is based on a monitoring system, which includes a management terminal and a sales terminal; the method includes: When the management terminal detects that the target product has left the factory, it obtains the predicted meteorological data of the transportation route planned for the target product. When the target product is delivered to the sales terminal, a first coefficient is determined based on the transportation risk coefficient and the pre-set storage risk level of the sales terminal, and added to the pre-set code of the target product to generate a sales code, which is then stored locally; the transportation risk coefficient represents the degree to which the transportation operation in the transportation route is affected by the meteorological conditions represented by the predicted meteorological data; When the sales terminal scans and stores the preset code of the target product, the sales code corresponding to the preset code is sent to the sales terminal, so that the sales terminal uses the sales code to update the preset code and stores it locally; Receive actual meteorological data of the sales location, and when the second coefficient is detected to be greater than the preset second coefficient threshold, determine whether the target product should be shipped based on the sales code; the second coefficient is obtained based on the warehousing risk level and the actual meteorological data, and characterizes the degree to which the target product is affected by natural disasters during the warehousing process; If the target product has not been shipped, a warehouse alarm message is sent to the sales department; Determining the first coefficient includes: The transportation risk coefficient is determined based on the driving status of the vehicle carrying the target product on the transportation route. The transportation risk coefficient when the driving status indicates that the transportation efficiency of the vehicle has not reached the expected level and the predicted meteorological data indicates that there are traffic hazards on the transportation route is greater than the transportation risk coefficient when the driving status indicates that the transportation efficiency of the vehicle has reached the expected level and the predicted meteorological data indicates that there are no traffic hazards on the transportation route. Based on the transportation risk coefficient, the warehousing risk level, and the serial number of the target product, construct available fields; The available fields are processed using a hash algorithm to obtain the first coefficient; Based on historical event data, samples and corresponding tags are constructed; each sample represents information such as the preset coding representation of historical products involved in the historical event to which it belongs, the storage risk level of the sales end of the historical product, and the natural disaster data involved in the historical event; the tag represents the degree of impact of the historical event on the historical product's natural disasters during the storage process. A pre-defined support vector machine model is trained using the samples and the labels to obtain a second support vector machine model; Upon receiving the actual meteorological data of the sales location, the second support vector machine model is used to determine the second coefficient.

2. The method as described in claim 1, characterized in that, The method further includes: If it is determined that the target product has not been shipped based on the sales code, then it is determined whether the target product has been shipped based on the preset code; If the target product has not been shipped, a warehouse alarm message is sent to the sales department.

3. The method as described in claim 2, characterized in that, The method further includes: If it is determined based on the preset code that the target product has been shipped, a theft alarm message is sent to the sales terminal.

4. The method as described in claim 3, characterized in that, The monitoring system also includes a monitoring terminal, and the method further includes: Send the warehouse alarm information and / or the theft alarm information to the monitoring terminal; After receiving the confirmation from the regulatory authority, the alarm is cancelled.

5. The method as described in claim 1, characterized in that, The method further includes: When the target product is inspected upon entry into the warehouse, a monitoring period is determined based on the product's expiration date and the storage risk level, and the timer is started; the duration of the monitoring period is less than or equal to the product's expiration date. When the timeout period ends, a product validity alarm message is sent to the sales department.

6. The method as described in claim 5, characterized in that, The method further includes: The time period of focus is obtained using a pre-trained first support vector machine model; the first support vector machine model is trained using historical data.

7. The method as described in claim 1, characterized in that, The method further includes: If the storage risk level is greater than a preset level threshold, when the target product is detected to be out of the warehouse, a third coefficient for the target product is determined; the third coefficient represents the sum of the second coefficients at each historical time point in the storage process of the target product; the historical time point is the time point when a meteorological event occurred in history; If the third coefficient is greater than the preset third coefficient threshold, a confirmation alarm message is sent to the sales end.

8. The method as described in claim 4, characterized in that, The method further includes: If the receipt of the warehouse alarm information indicates that the target product has a quality risk, then the target product is identified as the reference product. Based on the preset code, products that are found from the candidate products and whose similarity to the reference product is greater than a preset first similarity threshold, and whose predicted weather data of the sales location of the reference product is greater than a preset second similarity threshold than the actual weather data of the sales location of the reference product, are identified as risk products. Send an inspection alert to the sales department of the risky product.

Images