Goods abnormity early warning method, system and equipment for telecom operator

Abstract

The embodiment of the invention provides a goods abnormity early warning method, system and equipment for a telecom operator, and the method comprises the steps: determining whether a goods is an abnormal goods or not based on an index measurement value, a goods grade and a set index reference range; under the condition that abnormal goods exist in the multiple goods, the first proportion of the abnormal goods relative to the multiple goods is counted, under the condition that the first proportion is larger than a first proportion threshold value, production record information of the abnormal goods is obtained, and a processing time sequence curve is generated according to the production record information; performing similarity calculation on the processing time sequence curve and a set reference time sequence curve to obtain a similarity value, and determining an abnormal production link from each production link based on the processing time sequence curve and the reference time sequence curve under the condition that the similarity value is smaller than a preset similarity threshold value, and generating first early warning information containing a production link identifier corresponding to the abnormal production link, and sending the first early warning information to a preset management terminal. According to the scheme, the early warning efficiency can be improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of data processing, and in particular to a product abnormality early warning method, system and device for a telecommunications operator. BACKGROUND

[0002] With the continuous development of intelligent manufacturing technology, telecommunications operators provide various network service-related entity products to meet the needs of diversified network scenarios. Among them, specific entity products include communication cards, portable Wi-Fi, optical modems, routers, etc., which have become the infrastructure supporting the development of the digital economy. For telecommunications operators, dynamic monitoring of the entire life cycle of entity products has become a core requirement to ensure operational efficiency. In order to ensure service quality, telecommunications operators need to monitor the production and storage of products to improve delivery quality and stabilize inventory demand.

[0003] In related technologies, relevant personnel need to determine whether there are problems in the production process and storage process of products according to production experience, and output product early warning information according to the determination result to handle related abnormal problems. However, the aforementioned method has low early warning efficiency and is prone to problems of not timely early warning, thereby affecting the delivery quality of products. SUMMARY

[0004] The present application provides a product abnormality early warning method, system and device for a telecommunications operator, which solves the problem of low early warning efficiency in related technologies, which is prone to problems of not timely early warning and affects the delivery quality of products, and can improve the early warning efficiency, timely perform product abnormality early warning, and thereby ensure the delivery quality of products.

[0005] In a first aspect, the present application provides a product abnormality early warning method for a telecommunications operator, which comprises: obtaining index measurement values and product grades corresponding to a plurality of current products respectively, and determining whether the products are abnormal products based on the index measurement values, the product grades and a set index reference range; In the case where there are abnormal products in the plurality of products, a first proportion of the abnormal products relative to the plurality of products is counted, and in the case where the first proportion is greater than a first proportion threshold, production record information of the abnormal products is obtained, a processing time sequence curve is generated according to the production record information, and the processing time sequence curve records equipment operating parameters and processing time nodes detected at each production link; The similarity value is obtained by performing similarity calculation on the processing time sequence curve and a set reference time sequence curve, and in a case where the similarity value is less than a preset similarity threshold, an abnormal production link is determined from the respective production links based on the processing time sequence curve and the reference time sequence curve, a first early warning information containing a production link identifier corresponding to the abnormal production link is generated, and the first early warning information is sent to a preset management terminal.

[0006] In a second aspect, the present application further provides a goods abnormal early warning system of a telecom operator, comprising: An abnormal goods determination module is configured to acquire index measurement values and goods grades corresponding to a plurality of current goods respectively, and determine whether the goods are abnormal goods based on the index measurement values, the goods grades, and a set index reference range; A time sequence curve determination module is configured to, in a case where there are abnormal goods in the plurality of goods, count a first proportion of the abnormal goods relative to the plurality of goods, acquire production record information of the abnormal goods in a case where the first proportion is greater than a first proportion threshold, generate a processing time sequence curve according to the production record information, and record equipment operation parameters and processing time nodes detected by respective production links in the processing time sequence curve; A first early warning information determination module is configured to perform similarity calculation on the processing time sequence curve and a set reference time sequence curve to obtain a similarity value, determine an abnormal production link from the respective production links based on the processing time sequence curve and the reference time sequence curve in a case where the similarity value is less than a preset similarity threshold, generate a first early warning information containing a production link identifier corresponding to the abnormal production link, and send the first early warning information to a preset management terminal.

[0007] In a third aspect, the present application further provides a goods abnormal early warning device of a telecom operator, comprising: One or more processors; A storage device configured to store one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the goods abnormal early warning method of the telecom operator described in the present application.

[0008] In a fourth aspect, the present application further provides a non-volatile storage medium storing computer executable instructions, which are configured to execute the goods abnormal early warning method of the telecom operator described in the present application when executed by a computer processor.

[0009] In the present application, by acquiring the index measurement values and the product grades corresponding to the current plurality of products, it is determined whether the products are abnormal products based on the index measurement values, the product grades and the set index reference range. In the case where there are abnormal products in the plurality of products, the first proportion of the abnormal products relative to the plurality of products is counted, and in the case where the first proportion is greater than a first proportion threshold, the production record information of the abnormal products is acquired, a processing time sequence curve is generated according to the production record information, and the processing time sequence curve records the equipment operation parameters and the processing time nodes detected in each production link. The similarity value is obtained by similarity calculation of the processing time sequence curve and the set reference time sequence curve, and in the case where the similarity value is less than a preset similarity threshold, the abnormal production link is determined from each production link based on the processing time sequence curve and the reference time sequence curve, and the first warning information containing the production link identifier corresponding to the abnormal production link is generated. The first warning information is sent to a preset management terminal. In the above scheme, by combining the index measurement values, the product grades and the set index reference range, the abnormal products that do not meet the standards are screened out from the plurality of products, and the first proportion of the abnormal products relative to the plurality of products is counted to determine whether further confirmation is needed to determine whether there is production abnormality. By generating the processing time sequence curve according to the production record information and performing similarity calculation of the processing time sequence curve and the set reference time sequence curve to obtain the similarity value, it can be quickly compared and confirmed whether the overall production process is abnormal, and in the case where the similarity value is less than the preset similarity threshold, the abnormal production link can be accurately determined from each production link based on the processing time sequence curve and the reference time sequence curve. The first warning information can be generated and sent in time, which can improve the warning efficiency, timely product abnormal warning and guarantee the delivery quality of the products. BRIEF DESCRIPTION OF DRAWINGS

[0010] Figure 1 A flowchart of a product abnormal warning method of a telecommunications operator provided by an embodiment of the present application; Figure 2 A flowchart of a product abnormal warning method of a telecommunications operator provided by an embodiment of the present application, which includes a process of generating a processing time sequence curve; Figure 3 A flowchart of a product abnormal warning method of a telecommunications operator provided by an embodiment of the present application, which includes a process of determining an abnormal production link; Figure 4 A flowchart of a product abnormal warning method of a telecommunications operator provided by an embodiment of the present application, which includes a process of generating a second warning information based on an expiration risk value; Figure 5 A flowchart of a product abnormal warning method of a telecommunications operator provided by an embodiment of the present application, which includes a process of calculating an expiration risk value; Figure 6A flowchart of a telecommunication operator's abnormal goods early warning method provided by an embodiment of the present application, which comprises a process of determining whether a goods is an abnormal goods or not; Figure 7 A flowchart of another telecommunication operator's abnormal goods early warning method provided by an embodiment of the present application, which comprises a process of determining whether a goods is an abnormal goods or not; Figure 8 A structural block diagram of a telecommunication operator's abnormal goods early warning system provided by an embodiment of the present application; Figure 9 A structural schematic diagram of a telecommunication operator's abnormal goods early warning device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0011] The embodiments of the present application will be further described below in conjunction with the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the embodiments of the present application, but not to limit the embodiments of the present application. In addition, it should be noted that, for the convenience of description, only the parts related to the embodiments of the present application are shown in the drawings, but not all the structures.

[0012] The terms "first", "second", and the like in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be exchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than that illustrated or described herein, and the objects distinguished by "first", "second", etc. are usually a class, and do not limit the number of objects, for example, the first object can be one or more. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / ", generally indicates that the front and rear associated objects are in a "or" relationship.

[0013] The telecommunication operator's abnormal goods early warning method provided by the embodiments of the present application, the execution subject of each step can be a computer device, which refers to any electronic device with data computing, processing and storage capabilities, such as mobile phones, PC (Personal Computer), tablet computers and other terminal devices, or servers and other devices, which are not limited by the embodiments of the present application.

[0014] Figure 1 A flowchart of a telecommunication operator's abnormal goods early warning method provided by an embodiment of the present application, as shown in Figure 1 The telecommunication operator's abnormal goods early warning method provided by the embodiments of the present application, the execution subject of each step can be a computer device, which refers to any electronic device with data computing, processing and storage capabilities, such as mobile phones, PC (Personal Computer), tablet computers and other terminal devices, or servers and other devices, which are not limited by the embodiments of the present application. Step S101, obtaining the index measurement value and the goods grade corresponding to the current plurality of goods respectively, and determining whether the goods is an abnormal goods based on the index measurement value, the goods grade and the set index reference range.

[0015] The index measurement value can be measurement information of a key index parameter for verifying whether the performance of the goods meets the standard after production, and the goods grade can be performance level information of the goods predefined according to business requirements. In the operation process of a telecom operator, taking a communication card as an example, the index measurement value corresponding to the communication card can be a data transmission rate, a temperature limit, a humidity limit, etc., and the specific goods grade can be different grades such as a basic grade and an enhanced grade, which are distinguished from low to high in terms of performance requirements. Of course, the developer can also adaptively set the measurement index and the grade division according to the specific goods type in the actual application scenario, which is not limited herein. Different goods grades have different performance requirements, and their corresponding actual index ranges are different. In an embodiment, a preset mapping relationship can be queried based on the goods grade to determine a corresponding index reference range, and the index measurement value is compared with the index reference range to determine whether the goods is an abnormal goods. In an embodiment, a benchmark index reference range can be set, the index reference range is adjusted based on the goods grade to determine a target index reference range suitable for the goods, and the index measurement value is compared with the target index reference range to determine whether the goods is an abnormal goods.

[0016] In step S102, if there is an abnormal goods in the plurality of goods, a first proportion of the abnormal goods relative to the plurality of goods is counted, and if the first proportion is greater than a first proportion threshold, production record information of the abnormal goods is obtained, and a processing time sequence curve is generated according to the production record information, wherein the processing time sequence curve records equipment operation parameters and processing time nodes detected at each production link.

[0017] If the abnormal goods exist in the plurality of goods, a first proportion of the abnormal goods relative to the plurality of goods can be counted to determine a production yield of the plurality of goods of the batch. The first proportion threshold value can be adaptively set by a developer according to the actual application scene, the goods yield requirement, and the production experience data, which is not limited herein. If the first proportion is less than or equal to the first proportion threshold value, it can be considered that the number of abnormal goods in the plurality of goods belongs to an acceptable range, and can enter other test links set subsequently. If the first proportion is greater than the first proportion threshold value, it can be considered that more abnormal goods exist in the plurality of goods, and further production abnormality investigation is needed. The production record information can be the equipment running parameters of each production link at different processing time nodes. The equipment running parameters can be key parameter values of the equipment running monitored in the production process. Taking the production of a communication card as an example, different production links such as chip manufacturing, cutting, and packaging can be involved, and each production link corresponds to a starting time node and an ending time node. In the specific production process, equipment running parameters such as processing temperature, gas flow, and gas pressure can be involved, which are not limited herein. Therefore, the processing time sequence curve can be generated according to the production record information. The processing time sequence curve can record the equipment running parameters and the processing time nodes detected by each production link, and is used to reflect the specific processing running state and the processing step sequence of the equipment.

[0018] In step S103, the similarity calculation is performed on the processing time sequence curve and the set reference time sequence curve to obtain a similarity value. If the similarity value is less than a preset similarity threshold value, the abnormal production link is determined from each production link based on the processing time sequence curve and the reference time sequence curve, and the first warning information containing the production link identifier corresponding to the abnormal production link is generated. The first warning information is sent to a preset management terminal.

[0019] The reference time sequence curve can be a corresponding equipment operation parameter and processing time node when the equipment in each production link is in a normal processing state and is pre-generated. The similarity calculation can be dynamic time warping calculation, Euclidean distance calculation, or cosine similarity calculation, and the present application is not limited herein. By performing similarity calculation on the processing time sequence curve and the set reference time sequence curve, the degree of fit between the processing time sequence curve and the reference time sequence curve can be determined, and the production link that appears abnormal can be identified. If the similarity value is greater than or equal to a preset similarity threshold value, it can be considered that the degree of fit between the processing time sequence curve and the reference time sequence curve is high, and is within a tolerable deviation range, and prompt information containing the similarity result can be fed back to a preset management terminal to enable relevant personnel to continue to investigate other possible abnormal causes. If the similarity value is less than the preset similarity threshold value, it can be considered that the degree of fit between the processing time sequence curve and the reference time sequence curve is low, and there is a large deviation between them, and thus the processing time sequence curve and the reference time sequence curve can be further compared in terms of data of each production link to determine a specific abnormal production link. Finally, the first early warning information containing the production link identifier corresponding to the abnormal production link is sent to the preset management terminal, which can accurately remind relevant personnel of the specific production link that needs to be investigated.

[0020] In the above, by obtaining the indicator measurement values ​​and product grades corresponding to the current multiple goods respectively, based on the indicator measurement values, product grades and the set indicator reference range, it is determined whether the goods are abnormal goods; when there are abnormal goods among the multiple goods, a first proportion of the abnormal goods relative to the multiple goods is calculated, and when the first proportion is greater than a first proportion threshold, the production record information of the abnormal goods is obtained, and a processing timing curve is generated according to the production record information, and the processing timing curve records the equipment operating parameters and processing time nodes detected in each production link; a similarity calculation is performed between the processing timing curve and the set reference timing curve to obtain a similarity value, and when the similarity value is less than a preset similarity threshold, the abnormal production link is determined from each production link based on the processing timing curve and the reference timing curve, and a first warning information including a production link identifier corresponding to the abnormal production link is generated, and the first warning information is sent to a preset management terminal. In the above scheme, by combining the indicator measurement value, product grade and the set indicator reference range, substandard abnormal products are screened out from multiple products, and the first proportion of abnormal products relative to multiple products is counted to determine whether further confirmation is needed to determine whether there is a production abnormality. By generating a processing timing curve based on the production record information, and performing a similarity calculation on the processing timing curve and the set reference timing curve to obtain a similarity value, a quick comparison can be made to confirm whether there is an abnormality in the overall production process. When the similarity value is less than the preset similarity threshold, the abnormal production link is determined from each production link based on the processing timing curve and the reference timing curve. The production link where the abnormality occurs can be accurately confirmed, and the first warning information can be generated and sent in time, which can improve the warning efficiency, make a timely warning of product abnormalities, and ensure the shipment quality of the goods.

[0021] Figure 2 A flowchart of a method for early warning of abnormal goods of a telecommunications operator including a process of generating a processing timing curve is provided in an embodiment of the present application, such as Figure 2 As shown, the telecom operator's product abnormality warning method specifically includes the following steps: Step S201: Obtain indicator measurement values ​​and product grades corresponding to multiple current products, and determine whether the product is an abnormal product based on the indicator measurement values, product grades and the set indicator reference range.

[0022] In the case where there is an abnormal product in the plurality of products, a first proportion of the abnormal product with respect to the plurality of products is counted, in the case where the first proportion is greater than a first proportion threshold, production record information of the abnormal product is obtained, processing time nodes corresponding to each production link are extracted from the production record information, and equipment operation parameters corresponding to each processing time node are extracted, the equipment operation parameters corresponding to each processing time node are subjected to extreme value filtering to obtain target equipment operation parameters, and the processing time nodes corresponding to each production link and the target equipment operation parameters are fitted to obtain a processing timing curve.

[0023] Among them, the processing time nodes corresponding to each production link can be extracted from the production record information, for example, the starting time nodes and the ending time nodes corresponding to different processing steps, and different processing time nodes can monitor corresponding equipment operation parameters. Because data loss or serious deviation from the normal range may occur in the equipment monitoring process due to network jitter or data transmission abnormalities, etc., the equipment operation parameters corresponding to each processing time node can be subjected to extreme value filtering to obtain target equipment operation parameters. Finally, the processing time nodes corresponding to each production link and the target equipment operation parameters can be associated, and a processing timing curve can be fitted based on the time axis as a reference.

[0024] In the case where the similarity value is less than a preset similarity threshold, an abnormal production link is determined from each production link based on the processing timing curve and the reference timing curve, a first early warning information containing a production link identifier corresponding to the abnormal production link is generated, and the first early warning information is sent to a preset management terminal.

[0025] The above, by subjecting the equipment operation parameters corresponding to each processing time node to extreme value filtering to obtain target equipment operation parameters, the reliability and stability of the data can be improved, by fitting the processing time nodes corresponding to each production link and the target equipment operation parameters to obtain a processing timing curve, the actual running state information of the equipment in each production link, and the standard processing sequence and time consumption of the production process can be simultaneously fused, providing data support for subsequent determination of abnormal production links.

[0026] Figure 3 A flowchart of a product abnormal early warning method of a telecommunications operator containing a process for determining an abnormal production link provided by the embodiments of the present application is shown in Figure 3 The product abnormal early warning method of the telecommunications operator specifically includes the following steps: Step S301, obtaining index measurement values and product grades respectively corresponding to a plurality of current products, determining whether the products are abnormal products based on the index measurement values, the product grades, and a set index reference range.

[0027] In the case where the abnormal product exists in the plurality of products, a first proportion of the abnormal product with respect to the plurality of products is counted, in the case where the first proportion is greater than a first proportion threshold, production record information of the abnormal product is acquired, a processing time sequence curve is generated according to the production record information, and the processing time sequence curve records equipment operation parameters and processing time nodes detected by each production link.

[0028] In the case where the abnormal product exists in the plurality of products, a first proportion of the abnormal product with respect to the plurality of products is counted, in the case where the first proportion is greater than a first proportion threshold, production record information of the abnormal product is acquired, a processing time sequence curve is generated according to the production record information, and the processing time sequence curve records equipment operation parameters and processing time nodes detected by each production link.

[0029] The similarity value is obtained by similarity calculation of the processing time sequence curve and the set reference time sequence curve, and is used to compare the processing time sequence curve and the set reference time sequence curve from a global dimension, and to preliminarily determine whether the processing process is abnormal. If the similarity value is less than a preset similarity threshold, it can be considered that there is a large deviation between the processing time sequence curve and the reference time sequence curve, and further comparison can be performed in a local dimension unit. Thus, the corresponding first time sequence curve and the second time sequence curve can be extracted from the processing time sequence curve and the reference time sequence curve according to the starting time node and the ending time node corresponding to each production link, which means that the corresponding first time sequence curve and the second time sequence curve are extracted for each production link. Since the first time sequence curve and the second time sequence curve are composed of specific data points, each data point corresponds to a specific time node and a device running parameter. It can be understood that the associated data pairs are the data points corresponding to the same time node in the first time sequence curve and the second time sequence curve. Therefore, the data deviation comparison of the associated data pairs of the first time sequence curve and the second time sequence curve is equivalent to the point-by-point deviation comparison of the device running parameters. If the data deviation value of the device running parameters corresponding to the two associated data points is greater than a preset deviation threshold, it can be considered that the data deviation exceeds the normal fluctuation range, and it can be considered as the target associated data pair. The preset deviation threshold can be adaptively set by the developer according to the device production standard and experience data in the actual application scenario, which is not limited herein. By calculating a second proportion of the first number relative to the total number of associated data pairs, and comparing the second proportion with a second proportion threshold, it can be determined whether the data deviation between the first time sequence curve and the second time sequence curve belongs to occasional normal fluctuation or frequent abnormal fluctuation. If the second proportion is greater than the second proportion threshold, it can be considered that the first time sequence curve and the second time sequence curve have too large deviation, and the corresponding production link can be determined as an abnormal production link. The second proportion threshold can be adaptively set by the developer according to the device running characteristics and production experience data in the actual application scenario, which is not limited herein.

[0030] In step S304, first warning information containing the production link identifier corresponding to the abnormal production link is generated, and the first warning information is sent to a preset management terminal.

[0031] By comparing the data deviation of the associated data pairs of the first time sequence curve and the second time sequence curve, the curve comparison of each production link in a local dimension can be performed, which is beneficial to accurately positioning the abnormal production link. By calculating the second proportion of the first number relative to the total number of associated data pairs, the influence of occasional data fluctuation can be excluded, and the result reliability of the abnormal production link can be ensured.

[0032] Figure 4A flowchart of a goods abnormal early warning method of a telecommunications operator comprising a process of generating second early warning information based on an expiration risk value is provided for an embodiment of the present application, as shown in Figure 4 The goods abnormal early warning method of the telecommunications operator specifically comprises the following steps: Step S401, obtaining index measurement values and goods grades corresponding to a plurality of goods respectively, and determining whether the goods are abnormal goods based on the index measurement values, the goods grades, and a set index reference range.

[0033] Step S402, in the case where there is no abnormal goods in the plurality of goods, obtaining historical shipment information and a storable quantity, and calculating an expiration risk value according to the historical shipment information, the storable quantity, a quantity to be stored corresponding to the plurality of goods, and a preset shelf life.

[0034] Wherein, if there is no abnormal goods in the plurality of goods, it can be considered that the production process corresponding to the plurality of goods is normal, and the goods abnormal early warning can be further performed from the goods inventory management dimension. The historical shipment information can be the record of the storage and shipment of goods produced in the past period of time. The storable quantity can be the current available capacity of the warehouse. The quantity to be stored can be the total quantity of the plurality of goods to be stored. The preset shelf life can be the longest time during which the goods can maintain their physical, chemical, and functional characteristics in accordance with the prescribed standards under normal storage conditions. It should be noted that the historical shipment information can be used to judge the inventory backlog, the storable quantity and the quantity to be stored can be used to judge the current inventory occupation of the plurality of goods, and the preset shelf life can be used to provide expiration time information of the goods. Thus, the expiration risk value can be calculated according to the historical shipment information, the storable quantity, the quantity to be stored corresponding to the plurality of goods, and the preset shelf life, and the expiration risk value can be used to quantitatively represent the expiration risk of the plurality of goods after storage.

[0035] Step S403, in the case where the expiration risk value is greater than a preset risk threshold, generating second early warning information and sending the second early warning information to a preset management terminal.

[0036] Wherein, if the expiration risk value is greater than the preset risk threshold, it can be considered that the current plurality of goods has a high expiration risk, and abnormal early warning is needed to remind relevant personnel to make relevant production and inventory adjustments. The preset risk threshold can be adaptively set by the developer according to the risk control needs of goods inventory in the actual application scenario, which is not limited herein.

[0037] In the case where the abnormal goods exist in the plurality of goods, a first proportion of the abnormal goods with respect to the plurality of goods is counted, and in the case where the first proportion is greater than a first proportion threshold, production record information of the abnormal goods is acquired, a processing time sequence curve is generated according to the production record information, wherein the processing time sequence curve records equipment operation parameters and processing time nodes detected by each production link.

[0038] In the case where the abnormal goods exist in the plurality of goods, a first proportion of the abnormal goods with respect to the plurality of goods is counted, and in the case where the first proportion is greater than a first proportion threshold, production record information of the abnormal goods is acquired, a processing time sequence curve is generated according to the production record information, wherein the processing time sequence curve records equipment operation parameters and processing time nodes detected by each production link.

[0039] The above, by calculating the expiration risk value according to the historical delivery information, the storable quantity, the to-be-stored quantity corresponding to the plurality of goods and the preset shelf life, the expiration risk of the goods can be effectively evaluated in multiple dimensions, and in the case where the expiration risk value is greater than the preset risk threshold, the second warning information is generated, which can timely remind the relevant personnel to adjust the production and inventory, realize the fine management of the inventory, and reduce the expiration loss.

[0040] Figure 5 A flowchart of a goods abnormal warning method of a telecommunications operator provided by an embodiment of the present application is shown in FIG. 1, which includes the following steps: Figure 5 Step S501, acquiring index measurement values and goods grades corresponding to a plurality of current goods respectively, and determining whether the goods are abnormal goods based on the index measurement values, the goods grades and a set index reference range.

[0041] Step S502, in the case where the abnormal goods do not exist in the plurality of goods, acquiring historical delivery information and a storable quantity, calculating a stockpiling coefficient based on existing inventory, average delivery and a reference turnover period in the historical delivery information, calculating a time decay factor according to a preset shelf life and a preset decay function, dividing the to-be-stored quantity corresponding to the plurality of goods by the storable quantity to obtain a storage rate, and multiplying the storage rate, the stockpiling coefficient and the time decay factor to obtain an expiration risk value.

[0042] ​The existing inventory quantity can be the current existing inventory quantity of the produced goods, the average shipment quantity can be the shipment quantity of the goods per unit time, and the benchmark turnover days can be the expected continuous shipment time corresponding to the goods. Specifically, the calculation of the inventory backlog coefficient can be to multiply the average shipment quantity and the benchmark turnover days to obtain a to-be-shipped quantity, subtract the to-be-shipped quantity from the existing inventory quantity to obtain an inventory backlog quantity, and divide the inventory backlog quantity by the existing inventory quantity to obtain the inventory backlog coefficient, which is used to quantitatively represent the possible backlog degree of the goods. The preset decay function can be an exponential decay function, a linear decay function, etc., which is not limited herein. Specifically, the calculation of the time decay factor can be to subtract the production time of the goods from the current system time to obtain an interval duration, subtract the interval duration from the preset shelf life to obtain a remaining shelf life, and substitute the remaining shelf life into the preset decay function to obtain the time decay factor, wherein the longer the remaining shelf life, the smaller the time decay factor. In addition, the to-be-warehoused quantity and the warehousable quantity corresponding to the plurality of goods are divided to obtain a warehousing rate, which can be used to represent the inventory occupation of the plurality of goods. Finally, the warehousing rate, the inventory backlog coefficient, and the time decay factor are multiplied to obtain the expiration risk value, wherein the larger the warehousing rate, the larger the inventory backlog coefficient, and the larger the time decay factor, the larger the corresponding expiration risk value.

[0043] In step S503, the second warning information is generated when the expiration risk value is greater than the preset risk threshold, and the second warning information is sent to the preset management terminal.

[0044] In step S504, when there is an abnormal goods in the plurality of goods, a first proportion of the abnormal goods relative to the plurality of goods is counted, and when the first proportion is greater than a first proportion threshold, production record information of the abnormal goods is obtained, and a processing time sequence curve is generated according to the production record information, wherein the processing time sequence curve records the equipment operating parameters and the processing time nodes detected by each production link.

[0045] In step S505, the similarity between the processing time sequence curve and the set reference time sequence curve is calculated to obtain a similarity value, and when the similarity value is less than a preset similarity threshold, an abnormal production link is determined from each production link based on the processing time sequence curve and the reference time sequence curve, and a first warning information containing a production link identifier corresponding to the abnormal production link is generated, and the first warning information is sent to the preset management terminal.

[0046] The above, by multiplying the warehousing rate, the inventory backlog coefficient, and the time decay factor to obtain the expiration risk value, the expiration risk of the plurality of goods can be effectively quantitatively represented, and reliable reference information is provided for generating the second warning information.

[0047] Figure 6 A flowchart of a telecommunication operator's product abnormality early warning method including a process of determining whether a product is an abnormal product is provided for an embodiment of the present application, as shown in Figure 6 The telecommunication operator's product abnormality early warning method specifically includes the following steps: In step S601, the index measurement value and the product grade corresponding to each of the current plurality of products are obtained. Based on the index measurement value, the product grade, and the set index reference range, in the case where the index measurement value exceeds the index reference range, the tolerance ratio value is obtained according to the product grade by querying the set first correspondence relationship, the over-limit ratio value of the index measurement value relative to the index reference range is calculated, and in the case where the over-limit ratio value is greater than the tolerance ratio value, it is determined that the product is an abnormal product.

[0048] The first correspondence relationship can record the tolerance ratio value corresponding to different product grades. The tolerance ratio value can represent the tolerance degree allowed to exceed the index reference range under the corresponding product grade. For example, the tolerance ratio value corresponding to the basic grade product is smaller, and the tolerance ratio value corresponding to the enhanced grade product is larger. The over-limit ratio value can be the proportion of the part of the index measurement value exceeding the index reference range relative to the boundary threshold value. If the over-limit ratio value is greater than the tolerance ratio value, it can be considered that the index measurement value corresponding to the product seriously exceeds the index reference range, and thus it can be determined that the product is an abnormal product.

[0049] In step S602, in the case where there is an abnormal product in the plurality of products, the first proportion of the abnormal product relative to the plurality of products is calculated, in the case where the first proportion is greater than a first proportion threshold, the production record information of the abnormal product is obtained, and a processing time sequence curve is generated according to the production record information, wherein the processing time sequence curve records the equipment operation parameter and the processing time node detected at each production link.

[0050] In step S603, the similarity calculation of the processing time sequence curve and the set reference time sequence curve is performed to obtain a similarity value, in the case where the similarity value is less than a preset similarity threshold, the abnormal production link is determined from each production link based on the processing time sequence curve and the reference time sequence curve, and the first early warning information containing the production link identifier corresponding to the abnormal production link is generated, and the first early warning information is sent to a preset management terminal.

[0051] According to the above, the tolerance ratio value is obtained according to the product grade by querying the set first correspondence relationship, which can match different product grades to determine the tolerance adjustment degree of the index reference range, meet the product grading needs of actual application scenarios, and accurately determine whether the product is an abnormal product by calculating the over-limit ratio value of the index measurement value relative to the index reference range and comparing it with the tolerance ratio value.

[0052] Figure 7A flowchart of another method for early warning of abnormal goods of a telecommunications operator provided by an embodiment of the present application includes a process of determining whether the goods are abnormal goods, as shown in Figure 7 The method for early warning of abnormal goods of the telecommunications operator specifically includes the following steps: In step S701, the index measurement values and the grades of the current goods are obtained, and based on the index measurement values, the grades of the goods, and the set index reference range, the upper limit adjustment amplitude and the lower limit adjustment amplitude are obtained by querying the set second correspondence relationship according to the grade of the goods, the target index reference range is obtained by adjusting the index reference range according to the upper limit adjustment amplitude and the lower limit adjustment amplitude, and the goods are determined to be abnormal goods in the case that the index measurement value exceeds the target index reference range.

[0053] The second correspondence relationship can record the upper limit adjustment amplitude and the lower limit adjustment amplitude corresponding to different grades of goods. Since the performance requirements of different grades of goods are different, the index reference range can be used as a reference to adjust the index reference range according to the queried upper limit adjustment amplitude and lower limit adjustment amplitude. The upper limit adjustment amplitude and the lower limit adjustment amplitude can be positive increments or negative increments. Specifically, the upper limit adjustment amplitude can be added to the upper limit boundary threshold value, and the lower limit adjustment amplitude can be added to the lower limit boundary threshold value to obtain the target index reference range. If the index measurement value exceeds the target index reference range, it can be considered that the performance of the goods does not meet the expected requirements, and the goods can be further determined to be abnormal goods.

[0054] In step S702, in the case that there are abnormal goods in the plurality of goods, the first proportion of the abnormal goods relative to the plurality of goods is counted, and in the case that the first proportion is greater than a first proportion threshold value, the production record information of the abnormal goods is obtained, and a processing time sequence curve is generated according to the production record information, wherein the processing time sequence curve records the equipment operation parameters and the processing time nodes detected at each production link.

[0055] In step S703, the similarity between the processing time sequence curve and the set reference time sequence curve is calculated to obtain a similarity value, and in the case that the similarity value is less than a preset similarity threshold value, the abnormal production link is determined from each production link based on the processing time sequence curve and the reference time sequence curve, and the first warning information containing the production link identifier corresponding to the abnormal production link is generated and sent to a preset management terminal.

[0056] The upper limit adjustment amplitude and the lower limit adjustment amplitude are obtained through the second correspondence relationship set according to the goods grade query, the range adjustment increment corresponding to different goods grades can be determined, the target index reference range is obtained by adjusting the index reference range according to the upper limit adjustment amplitude and the lower limit adjustment amplitude, the target index reference range matched with the goods grade can be determined, and finally, the index measurement value is compared with the target index reference range, so that whether the goods is an abnormal goods can be accurately judged.

[0057] Figure 8 A structural block diagram of a goods abnormal early warning system of a telecom operator is provided for the embodiments of the present application. The system is configured to execute the goods abnormal early warning method of the telecom operator provided by the above embodiments, and has the corresponding function modules and beneficial effects of the execution method. As shown in the figure, the system specifically includes: Figure 8 An abnormal goods determination module 101 is configured to obtain index measurement values and goods grades corresponding to a plurality of current goods respectively, and determine whether the goods are abnormal goods based on the index measurement values, the goods grades and the set index reference range; A time sequence curve determination module 102 is configured to, in the case that there are abnormal goods in the plurality of goods, count a first proportion of the abnormal goods relative to the plurality of goods, obtain production record information of the abnormal goods in the case that the first proportion is greater than a first proportion threshold, generate a processing time sequence curve according to the production record information, and record the equipment operation parameters and the processing time nodes detected at each production link in the processing time sequence curve; A first early warning information determination module 103 is configured to perform similarity calculation on the processing time sequence curve and the set reference time sequence curve to obtain a similarity value, determine an abnormal production link from each production link based on the processing time sequence curve and the reference time sequence curve in the case that the similarity value is less than a preset similarity threshold, generate first early warning information containing a production link identifier corresponding to the abnormal production link, and send the first early warning information to a preset management terminal.

[0058] ​The above, by acquiring the index measurement value and the product grade corresponding to the current plurality of goods respectively, based on the index measurement value, the product grade and the set index reference range, determine whether the goods is an abnormal goods; in the case of a plurality of goods exist abnormal goods, statistics abnormal goods relative to the first proportion of a plurality of goods, in the first proportion is greater than the first proportion threshold, the production record information of the abnormal goods is acquired, and the processing time sequence curve is generated according to the production record information. The processing time sequence curve records the equipment operating parameter and the processing time node detected by each production link; the similarity calculation is carried out between the processing time sequence curve and the set reference time sequence curve to obtain the similarity value, in the case of the similarity value is less than the preset similarity threshold, the abnormal production link is determined from each production link based on the processing time sequence curve and the reference time sequence curve, and the first early warning information containing the production link identifier corresponding to the abnormal production link is generated. The first early warning information is sent to the preset management terminal. In the above scheme, the index measurement value, the product grade and the set index reference range are combined to screen out the abnormal goods that do not meet the standard from a plurality of goods, and the first proportion of the abnormal goods relative to a plurality of goods is counted. It is judged whether further confirmation is needed to determine whether there is production abnormality. The processing time sequence curve is generated according to the production record information, and the similarity calculation is carried out between the processing time sequence curve and the set reference time sequence curve to obtain the similarity value. The overall production process can be quickly compared and confirmed whether there is an abnormality. In the case of the similarity value is less than the preset similarity threshold, the abnormal production link is determined from each production link based on the processing time sequence curve and the reference time sequence curve. The production link that appears abnormal can be accurately confirmed, and the first early warning information can be generated and sent in time. The early warning efficiency can be improved, the goods abnormal early warning can be carried out in time, and the goods delivery quality can be guaranteed.

[0059] In one possible embodiment, the time sequence curve determination module 102 is further configured to: extract the processing time node corresponding to each production link and the equipment operating parameter corresponding to each processing time node from the production record information; carry out extreme value filtering on the equipment operating parameter corresponding to each processing time node to obtain the target equipment operating parameter; fit the processing time node and the target equipment operating parameter corresponding to each production link to obtain the processing time sequence curve.

[0060] In one possible embodiment, the first early warning information determination module 103 is further configured to: extract the first time sequence curve and the second time sequence curve corresponding to each production link from the processing time sequence curve and the reference time sequence curve respectively according to the start time node and the end time node corresponding to each production link; carry out data deviation comparison on the first time sequence curve and the second time sequence curve to screen out the first number of target associated data pairs with a data deviation value greater than a preset deviation threshold. calculate a second proportion of the first quantity relative to a total quantity of the associated data pairs, and determine the production link as an abnormal production link in a case where the second proportion is greater than a second proportion threshold.

[0061] In one possible embodiment, the device further comprises a second early warning information determination module configured to: In a case where there is no abnormal goods in the plurality of goods, obtain historical delivery information and a storable quantity, and calculate an expiration risk value according to the historical delivery information, the storable quantity, a quantity to be stored corresponding to the plurality of goods, and a preset shelf life; generate second early warning information in a case where the expiration risk value is greater than a preset risk threshold, and send the second early warning information to a preset management terminal.

[0062] In one possible embodiment, the second early warning information determination module is further configured to: calculate an inventory backlog coefficient based on an existing inventory quantity, an average delivery quantity, and a baseline turnover period in the historical delivery information; calculate a time decay factor according to the preset shelf life and a preset decay function; divide the quantity to be stored corresponding to the plurality of goods by the storable quantity to obtain a storage rate, and multiply the storage rate, the inventory backlog coefficient, and the time decay factor to obtain the expiration risk value.

[0063] In one possible embodiment, the abnormal goods determination module 101 is further configured to: obtain a tolerance proportion value according to a first correspondence relationship set according to the goods grade in a case where the index measurement value is outside the index reference range; calculate an over-limit proportion value of the index measurement value relative to the index reference range; determine the goods as abnormal goods in a case where the over-limit proportion value is greater than the tolerance proportion value.

[0064] In one possible embodiment, the abnormal goods determination module 101 is further configured to: obtain an upper limit adjustment amplitude value and a lower limit adjustment amplitude value according to a second correspondence relationship set according to the goods grade; adjust the index reference range according to the upper limit adjustment amplitude value and the lower limit adjustment amplitude value to obtain a target index reference range; determine the goods as abnormal goods in a case where the index measurement value is outside the target index reference range.

[0065] Figure 9 A structural schematic diagram of a goods abnormal early warning device of a telecommunications operator provided by an embodiment of the present application is shown in FIG. 1. Figure 9As shown, the device includes a processor 201, a memory 202, an input device 203 and an output device 204; the number of processors 201 in the device can be one or more, Figure 9 The processor 201 in the device is taken as an example. The processor 201, the memory 202, the input device 203 and the output device 204 in the device can be connected through a bus or other means, Figure 9 The memory 202 is taken as an example. The memory 202 can be configured to store software programs, computer executable programs and modules, such as program instructions / modules of the abnormal product early warning method of the telecommunications carrier. The processor 201 executes the software programs, instructions and modules stored in the memory 202, thereby performing various functional applications and data processing of the device, that is, implementing the abnormal product early warning method of the telecommunications carrier. The input device 203 can be configured to receive input digital or character information, and generate key signal input related to user settings and function control of the device. The output device 204 can include a display device such as a display screen.

[0066] The above-provided abnormal product early warning device of the telecommunications carrier can be used to execute the abnormal product early warning method of the telecommunications carrier provided by any of the above embodiments, and has corresponding functions and beneficial effects.

[0067] The embodiments of the present application also provide a non-volatile storage medium containing computer executable instructions, which are configured to execute an abnormal product early warning method of a telecommunications carrier described in the above embodiments when executed by a computer processor, and the method comprises: obtaining index measurement values and product grades corresponding to a plurality of current products respectively, determining whether the products are abnormal products based on the index measurement values, the product grades and the set index reference range; in the case that there are abnormal products in the plurality of products, statistics the first proportion of the abnormal products relative to the plurality of products, in the case that the first proportion is greater than a first proportion threshold, obtaining production record information of the abnormal products, generating a processing time sequence curve according to the production record information, the processing time sequence curve recording equipment operating parameters and processing time nodes detected at each production link; performing similarity calculation on the processing time sequence curve and the set reference time sequence curve to obtain a similarity value, in the case that the similarity value is less than a preset similarity threshold, determining an abnormal production link from each production link based on the processing time sequence curve and the reference time sequence curve, and generating first early warning information containing a production link identifier corresponding to the abnormal production link, and sending the first early warning information to a preset management terminal.

[0068] Storage medium - any of various types of memory devices or storage devices. The term "storage medium" is intended to include: installation media, such as CD-ROMs, floppy disks, or tape devices; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media, optical storage; registers or other similar types of memory elements, etc. Storage media may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the first computer system in which the program is executed, or may be located in a different second computer system that is connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media residing in different locations (e.g., in different computer systems connected via a network). The storage medium may store program instructions (e.g., embodied as a computer program) that can be executed by one or more processors.

[0069] Of course, the storage medium containing computer-executable instructions provided in the embodiment of the present application is not limited to the above-mentioned method for warning of abnormal goods of telecom operators, and can also execute relevant operations in the method for warning of abnormal goods of telecom operators provided in any embodiment of the present application.

[0070] It should be noted that the numbering of each step in this solution is only used to describe the overall design framework of this solution, and does not represent the necessary order relationship between the steps. On the basis that the overall implementation process conforms to the overall design framework of this solution, it belongs to the protection scope of this solution, and the order of precedence in the form of text when describing is not an exclusive limitation on the specific implementation process of this solution. Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. In a typical configuration, the computing device includes one or more processors (CPU), input / output interface, network interface and memory. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

[0071] It is also to be noted that the terms "comprising", "including", and any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises a... " does not, without more constraints, exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0072] Note that the above merely describes preferred embodiments of the present application and the applied technical principles. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, reconfigurations, and substitutions can be made without departing from the scope of the present application. Therefore, although the present application has been described in detail through the above embodiments, the present application is not limited to the above embodiments, and can include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A method for early warning of abnormal goods of a telecommunications operator, characterized in that: include: Obtaining indicator measurement values ​​and product grades corresponding to the current plurality of products, and determining whether the products are abnormal products based on the indicator measurement values, the product grades, and a set indicator reference range; If abnormal goods exist among the multiple goods, a first proportion of the abnormal goods relative to the multiple goods is calculated; if the first proportion is greater than a first ratio threshold, production record information of the abnormal goods is obtained, and a processing timing curve is generated based on the production record information, where the processing timing curve records equipment operating parameters and processing time nodes detected in each production link; A similarity calculation is performed on the processing timing curve and the set reference timing curve to obtain a similarity value. When the similarity value is less than a preset similarity threshold, the abnormal production link is determined from the various production links based on the processing timing curve and the reference timing curve, and a first warning information including a production link identifier corresponding to the abnormal production link is generated, and the first warning information is sent to a preset management terminal.

2. The method for early warning of abnormal goods of telecommunications operators according to claim 1, characterized in that: Generating a processing timing curve according to the production record information includes: Extracting the processing time nodes corresponding to each production link and the equipment operating parameters corresponding to each processing time node from the production record information; Filtering out extreme values ​​of the equipment operating parameters corresponding to each processing time node to obtain target equipment operating parameters; The processing time nodes corresponding to the various production links and the target equipment operating parameters are fitted to obtain a processing timing curve.

3. The method for early warning of abnormal goods of telecommunications operators according to claim 1, characterized in that: The determining of an abnormal production link from the various production links based on the processing timing curve and the reference timing curve includes: Extracting the corresponding first timing curve and second timing curve from the processing timing curve and the reference timing curve respectively according to the start time node and the end time node corresponding to each of the production links; Comparing the data deviations of the associated data pairs of the first timing curve and the second timing curve to screen out a first number of target associated data pairs whose data deviation values ​​are greater than a preset deviation threshold; A second proportion of the first quantity relative to the total quantity of the associated data pairs is calculated, and when the second proportion is greater than a second proportion threshold, the production link is determined to be an abnormal production link.

4. The method for early warning of abnormal goods of telecommunications operators according to claim 1, characterized in that: After determining whether the product is an abnormal product, the method further includes: If no abnormal products exist among the multiple products, historical shipping information and available warehousing quantities are obtained, and an expiration risk value is calculated based on the historical shipping information, the available warehousing quantities, the quantities to be warehousing corresponding to the multiple products, and the preset shelf life; When the expiration risk value is greater than a preset risk threshold, second warning information is generated and sent to the preset management terminal.

5. The method for early warning of abnormal goods of telecommunications operators according to claim 4, characterized in that: The calculating of the expiration risk value according to the historical shipment information, the available warehousing quantity, the corresponding quantities to be warehousing of the multiple products, and the preset shelf life includes: Calculate the inventory backlog coefficient based on the existing inventory, average shipment volume, and benchmark turnover days in the historical shipment information; Calculate a time decay factor based on the preset shelf life and the preset decay function; The warehousing rate is obtained by dividing the quantity to be warehousing corresponding to the multiple goods by the quantity available for warehousing, and the expiration risk value is obtained by multiplying the warehousing rate, the inventory backlog coefficient and the time decay factor.

6. The method for early warning of abnormal goods of telecommunications operators according to claim 1, characterized in that: Determining whether the product is an abnormal product includes: In the case where the indicator measurement value exceeds the indicator reference range, obtaining a tolerance ratio value according to the first corresponding relationship set by the product grade query; Calculating the excess ratio of the indicator measurement value relative to the indicator reference range; When the over-limit ratio value is greater than the tolerance ratio value, the product is determined to be abnormal product.

7. The method for early warning of abnormal goods of telecommunications operators according to claim 1, characterized in that: Determining whether the product is an abnormal product includes: Obtaining an upper limit adjustment amplitude and a lower limit adjustment amplitude according to a second corresponding relationship set by the product grade query; Adjusting the indicator reference range according to the upper limit adjustment amplitude and the lower limit adjustment amplitude to obtain a target indicator reference range; When the indicator measurement value exceeds the target indicator reference range, the product is determined to be abnormal product.

8. A goods abnormality warning system for telecommunications operators, characterized by: include: an abnormal product determination module configured to obtain indicator measurement values ​​and product grades corresponding to multiple current products, and determine whether the product is an abnormal product based on the indicator measurement values, the product grade, and a set indicator reference range; a timing curve determination module configured to, when abnormal goods exist among the plurality of goods, calculate a first proportion of the abnormal goods relative to the plurality of goods, obtain production record information of the abnormal goods when the first proportion is greater than a first ratio threshold, and generate a processing timing curve based on the production record information, wherein the processing timing curve records equipment operating parameters and processing time nodes detected at each production link; The first warning information determination module is configured to perform similarity calculation on the processing timing curve and the set reference timing curve to obtain a similarity value. When the similarity value is less than a preset similarity threshold, the abnormal production link is determined from the various production links based on the processing timing curve and the reference timing curve, and a first warning information including a production link identifier corresponding to the abnormal production link is generated, and the first warning information is sent to a preset management terminal.

9. A telecommunications operator's product abnormality warning device, comprising: one or more processors; A storage device configured to store one or more programs, when the one or more programs are executed by the one or more processors, enables the one or more processors to implement the goods abnormality warning method for telecommunications operators according to any one of claims 1-7.

10. A non-volatile storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by a computer processor, are configured to execute the goods abnormality early warning method for telecommunications operators according to any one of claims 1 to 7.

Images