CN114266473B - Supply chain demand prediction system and method based on data analysis - Google Patents
Supply chain demand prediction system and method based on data analysis Download PDFInfo
- Publication number
- CN114266473B CN114266473B CN202111571430.5A CN202111571430A CN114266473B CN 114266473 B CN114266473 B CN 114266473B CN 202111571430 A CN202111571430 A CN 202111571430A CN 114266473 B CN114266473 B CN 114266473B
- Authority
- CN
- China
- Prior art keywords
- data
- downstream node
- risk
- downstream
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000007405 data analysis Methods 0.000 title claims abstract description 26
- 238000004519 manufacturing process Methods 0.000 claims abstract description 46
- 238000004458 analytical method Methods 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 238000011144 upstream manufacturing Methods 0.000 claims description 12
- 239000013598 vector Substances 0.000 claims description 7
- 238000013459 approach Methods 0.000 claims description 6
- 238000013075 data extraction Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 4
- 239000003086 colorant Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000116 mitigating effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000001746 injection moulding Methods 0.000 description 1
- 238000013058 risk prediction model Methods 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Abstract
The application discloses a supply chain demand prediction system and a method based on data analysis, comprising a data preprocessing system and a model building analysis system; the data preprocessing system is used for analyzing historical predicted data, historical sales data and residual stock quantity data corresponding to the predicted data, extracting characteristic values corresponding to the historical data and judging risk values of the existing data; the model building module is used for judging comprehensive risk bearing capacity values which can be borne by different downstream nodes according to the risk values of the existing data, and adding the downstream nodes to distribute production tasks according to the comprehensive risk bearing capacity values so as to share risks; when detecting that the actual error predicted by one downstream node due to the supply chain is larger, adopting the method for adding the downstream node reduces the phenomenon that the downstream node frequently breaks due to the larger error. Through the establishment of the model, early warning can be carried out when the risk born by the downstream nodes is large, countermeasures can be taken, and the loss of one or more downstream nodes is reduced.
Description
Technical Field
The application relates to the technical field of data analysis, in particular to a supply chain demand prediction system and method based on data analysis.
Background
With the development of the internet and electronic commerce, more and more businesses cooperate together to spend various risk events, such as: inventory hold, inventory no-cargo, etc., thus, in order to avoid the above problems, the supply chain needs to determine the inventory quantity predicted by the supply chain according to the current market environment, the number of competing industries, and the marketing strategy, so as to issue the required inventory quantity to the downstream node (cooperator), and therefore, the decision of the supply chain is often critical;
although the decision of the supply chain is made according to the prediction before the actual occurrence, the result is predicted by the history demand information Pan Dun, but the predicted result always generates errors, and the current market aims at how to improve the prediction method to obtain accurate results, so as to reduce the prediction errors, but the actual comprehensive errors are always unavoidable, so that a method is required to avoid the increase of the errors;
in patent No.: 202011119200.0, a supply chain risk prediction model is set according to a training sample to perform training, so that after a risk event occurs in a target object, the probability of risk occurrence in other objects can be predicted, and early warning is provided.
Disclosure of Invention
The present application is directed to a supply chain demand prediction system and method based on data analysis, so as to solve the above-mentioned problems in the prior art.
In order to solve the technical problems, the application provides the following technical scheme: a supply chain demand prediction system based on data analysis comprises a data preprocessing system and a model building analysis system;
the data preprocessing system is used for analyzing historical predicted data, historical sales data and residual stock quantity data corresponding to the predicted data, extracting characteristic values corresponding to the historical data and judging risk values of the existing data;
the model building module is used for judging comprehensive risk bearing capacity values which can be borne by different downstream node companies according to the risk values of the existing data, and adding downstream nodes to distribute production tasks according to the comprehensive risk bearing capacity values so as to share risks.
Further, the data preprocessing system comprises a data extraction module and a data analysis module;
the data extraction module is used for acquiring historical sales data and residual stock quantity data, analyzing residual stock data corresponding to the lowest historical sales data and the highest historical sales data, comparing the residual stock data with predicted stock data, and recording and extracting corresponding data with data values smaller than the lowest sales data and corresponding data larger than the highest sales data;
and the data analysis module is used for analyzing that the corresponding data has high risk degree when detecting that the data extracted according with the conditions are present.
Further, the model building analysis system comprises a supply chain prediction difference analysis module, a risk sharing module, a risk bearing capacity judging module and a production quantity distribution and adjustment module;
the supply chain prediction difference analysis module is used for analyzing whether the difference between the production data required by the supply chain and the actual residual inventory data is larger than a first preset value or not when detecting that the risk value is larger than the standard risk value;
the risk sharing module shares risks born by one node by arranging a plurality of downstream nodes; mitigating the independent risk experienced by a single node;
the risk bearing capacity judging module is used for calling data of the downstream node and analyzing the comprehensive risk bearing capacity value which can be borne by the downstream node;
the production quantity distribution adjusting module distributes production tasks according to risks born by different downstream nodes, so that risks born by one downstream node independently are reduced.
Further, a supply chain demand prediction method based on data analysis specifically comprises the following steps:
acquiring historical data, namely historical sales data, residual stock quantity data and forecast inventory data, wherein a supply chain prejudges the quantity of required commodity production according to market environment, sales promotion activities and the past forecast data, distributes different production quantities to a plurality of downstream nodes according to the forecast production quantity and different parts, judges whether the quantity is larger than a first preset value according to the difference between the actual sold quantity of the commodity and the forecast quantity, and analyzes the comprehensive risk bearing capacity value born by the plurality of downstream nodes;
judging whether the comprehensive risk bearing capacity value borne by the downstream nodes is larger than a second preset value or not according to the comprehensive risk bearing capacity values borne by the downstream nodes, if the comprehensive risk bearing capacity value is smaller than the second preset value, adding the downstream nodes to distribute the production quantity of the parts, modeling according to the production quantity, and reducing the risk value of the independent nodes; when the comprehensive risk bearing capacity value is smaller than the second preset value, no downstream node is needed to be added.
Further, the comprehensive risk bearing capacity value W borne by the downstream node needs to be increased to set the downstream node to share the risk when the detection that W is larger than the second preset value, and does not need to be increased to set the downstream node to share the risk when the detection that W is smaller than the second preset value;
W＝W total (S) -a ij *k-W Removing ；
Wherein W is Total (S) Refers to the total value of total comprehensive risk bearing capacity, a ij Refers to the importance degree, k, of i parts in the rest parts j 1 Refers to risk factor, W Removing Refers to the comprehensive risk bearing capacity value of the last year;
wherein P is i Refers to the funds used in the production of part i, P i+j All active funds of the downstream node;
when P i Occupy P i+j When the probability of (2) is lower than a third preset value, the downstream node is indicated to still have residual active funds to produce other parts besides the current part, and the risk value of the downstream node is indicated to be low; when P i Occupy P i+j When the probability of (2) is higher than the third preset value, the downstream node is indicated to have a high risk value, wherein the downstream node comprises the existing funds for producing the current part, and the remaining active funds cannot produce other parts.
When the comprehensive risk bearing capacity value borne by the downstream node is detected to be low, the downstream node is added, wherein the added downstream node meets the following formula:
wherein: h refers to the degree of association, C t The method is characterized in that the method refers to the number of downstream node chains for processing products for upstream nodes, S refers to the association coefficient for producing the same products with the downstream nodes, and Y refers to the number of enterprises of the upstream nodes and the downstream nodes;
when H is lower than a fourth preset value, the association degree between the downstream node and the downstream node to be added is low, when H is higher than the fourth preset value, the association degree between the downstream node and the downstream node to be added is high, and the similarity between the comprehensive risk bearing capacity value born by the added downstream node and the last downstream node is further detected;
when the similarity value of sim is detected to approach 1, W is represented 1 And W is equal to 2 If the risk value of the downstream node is lower than a second preset value, the downstream node cannot be added; when the similarity of sim is detected to approach 0, W is represented 1 And W is equal to 2 If the risk value of the downstream node is lower than a second preset value, the downstream node can be added;
wherein sim refers to the degree of similarity,refers to a vector of the first downstream node comprehensive risk bearing capacity values, +>Refers to a vector of the second downstream node comprehensive risk bearing capacity values, |w 1 I is the pointing quantity W 1 Is, |W 2 I is the pointing quantity W 2 Is a mold of (a).
The newly added downstream node distributes part production tasks, when the comprehensive risk bearing capacity value |W of the downstream node is detected x1 -W x2 When |=0, the number of production parts is equally apportioned; when the comprehensive risk tolerance value |W of the downstream node is detected x1 -W x2 |<0, when the downstream node x is detected 2 When the bearing capacity value of the comprehensive risk is larger than a fifth preset value, adding downstream nodes to apportion risks; when the downstream node x is detected 2 When the comprehensive risk bearing capacity value is smaller than the fifth preset value, the number of the parts allocated by the downstream node x2 is larger than that of the downstream node x 1 The number of parts allocated.
The added downstream node should also acquire the following conditions: any one or any combination of registered capital of the downstream node, liability information of the downstream node, and worker scale involved in part production is obtained.
Compared with the prior art, the application has the following beneficial effects:
by arranging the downstream nodes, risk errors can be effectively reduced when errors occur in supply chain prediction, and the production quantity born by different downstream nodes is analyzed by analyzing the comprehensive risk bearing capacity values born by the downstream nodes, so that the risk born by the independent downstream nodes can be reduced; enterprise losses through multi-node setup can also be reduced;
the deviation value of the error is obtained according to the historical prediction error judgment, the number of the nodes to be set can be timely and efficiently analyzed, risks born by enterprises are reduced, and the distribution number of the nodes is reasonably controlled.
Drawings
The accompanying drawings are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, serve to explain the application. In the drawings:
FIG. 1 is a schematic diagram illustrating steps of a supply chain demand prediction system and method based on data analysis according to the present application;
FIG. 2 is a schematic diagram illustrating a node distribution of a supply chain demand prediction system and method based on data analysis according to the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1-2, the present application provides the following technical solutions:
wherein: the first preset value refers to a standard prediction error;
the second predicted value refers to a standard comprehensive risk bearing capacity value borne by the downstream node;
the third preset value refers to the probability of the standard;
the fourth preset value refers to the standard association degree;
the fifth preset value refers to the integrated risk tolerance value that the newly added downstream node assumes compared to the downstream node.
A supply chain demand prediction system based on data analysis comprises a data preprocessing system and a model building analysis system;
the data preprocessing system is used for analyzing historical predicted data, historical sales data and residual stock quantity data corresponding to the predicted data, extracting characteristic values corresponding to the historical data and judging risk values of the existing data;
the model building module is used for judging comprehensive risk bearing capacity values which can be borne by different downstream node companies according to the risk values of the existing data, and adding downstream nodes to distribute production tasks according to the comprehensive risk bearing capacity values so as to share risks.
Further, the data preprocessing system comprises a data extraction module and a data analysis module;
the data extraction module is used for acquiring historical sales data and residual stock quantity data, analyzing residual stock data corresponding to the lowest historical sales data and the highest historical sales data, comparing the residual stock data with predicted stock data, and recording and extracting corresponding data with data values smaller than the lowest sales data and corresponding data larger than the highest sales data;
and the data analysis module is used for analyzing that the corresponding data has high risk degree when detecting that the data extracted according with the conditions are present.
Further, the model building analysis system comprises a supply chain prediction difference analysis module, a risk sharing module, a risk bearing capacity judging module and a production quantity distribution and adjustment module;
the supply chain prediction difference analysis module is used for analyzing whether the difference between the production data required by the supply chain and the actual residual inventory data is larger than a first preset value or not when detecting that the risk value is larger than the standard risk value;
the risk sharing module shares risks born by one node by arranging a plurality of downstream nodes; mitigating the independent risk experienced by a single node;
the risk bearing capacity judging module is used for calling data of the downstream node and analyzing the comprehensive risk bearing capacity value which can be borne by the downstream node;
the production quantity distribution adjusting module distributes production tasks according to risks born by different downstream nodes, so that risks born by one downstream node independently are reduced.
Further, a supply chain demand prediction method based on data analysis specifically comprises the following steps:
acquiring historical data, prejudging the number of required commodity production by a supply chain according to market environment, sales promotion activities and past predicted data, distributing different production numbers to a plurality of downstream nodes according to the predicted production numbers and different parts, judging whether the number is larger than a first preset value according to the difference between the actual sold number of the commodity and the predicted number, and analyzing the comprehensive risk bearing capacity value born by the plurality of downstream nodes;
the presented historical data includes historical sales data, remaining inventory data, and forecast inventory data;
judging whether the comprehensive risk bearing capacity value borne by the downstream nodes is larger than a second preset value or not according to the comprehensive risk bearing capacity values borne by the downstream nodes, if the comprehensive risk bearing capacity value is smaller than the second preset value, adding the downstream nodes to distribute the production quantity of the parts, modeling according to the production quantity, and reducing the risk value of the independent nodes; when the comprehensive risk bearing capacity value is smaller than the second preset value, no downstream node is needed to be added.
Further, the comprehensive risk bearing capacity value W borne by the downstream node needs to be increased to set the downstream node to share the risk when the detection that W is larger than the second preset value, and does not need to be increased to set the downstream node to share the risk when the detection that W is smaller than the second preset value;
W＝W total (S) -a ij *k-W Removing ；
Wherein W is Total (S) Refers to the total value of total comprehensive risk bearing capacity, a ij Refers to the importance degree, k, of i parts in the rest parts j 1 Refers to risk factor, W Removing Refers to the comprehensive risk bearing capacity value of the last year;
wherein P is i Refers to the funds used in the production of part i, P i+j All active funds of the downstream node;
when P i Occupy P i+j When the probability of (2) is lower than a third preset value, the downstream node is indicated to still have residual active funds to produce other parts besides the current part, and the risk value of the downstream node is indicated to be low; when P i Occupy P i+j When the probability of (2) is higher than a third preset value, the downstream node is indicated to contain the existing funds to produce the current part, and the remaining movable funds can not produce other parts, so that the risk value of the downstream node is indicated to be high;
after the supply chain predicts the number of the sold products, the production number is allocated to different downstream nodes according to the number of the parts contained in the products, for example, when the upstream node is a mobile phone and the upstream node is a core system and a chip of the mobile phone, the downstream node sells after-sale services, mobile phone shells and various mobile phone parts, wherein when the mobile phone shells are sold, the downstream node is divided into the following downstream nodes, for example: the injection molding machine is specially used for producing shells with different types and colors, and distributing downstream nodes to produce parts such as a rear cover, a front cover and the like of the mobile phone, when one of the downstream nodes is specially used for producing shells with different colors, but because the quantity of the upstream nodes is excessive and the downstream nodes are used for throwing most of funds on the shells, in order to avoid the excessive risk of the downstream nodes, a plurality of downstream nodes are arranged to share part quantity so as to manufacture the mobile phone shell;
in the above formula, a is set ij Further analyzing the importance of the currently manufactured part in the downstream node, and analyzing whether there are remaining flowing funds in the current downstream nodeOn the project, correspondingly analyzing whether the comprehensive capacity of the company can support all risks, a ij Plays a significant role; in the analysis process, the comprehensive risk tolerance value born by the company in the last year can be deduced, and therefore, the influence of the comprehensive risk tolerance value in the last year on the risk tolerance value born by the node downstream in the present year can be taken as an important factor for judging the comprehensive risk tolerance value of the node downstream in the present year.
When the comprehensive risk bearing capacity value borne by the downstream node is detected to be low, the downstream node is added, wherein the added downstream node meets the following formula:
wherein: h refers to the degree of association, C t The method is characterized in that the method refers to the number of downstream node chains for processing products for upstream nodes, S refers to the association coefficient for producing the same products with the downstream nodes, and Y refers to the number of enterprises of the upstream nodes and the downstream nodes;
when H is lower than a fourth preset value, the association degree between the downstream node and the downstream node to be added is low, when H is higher than the fourth preset value, the association degree between the downstream node and the downstream node to be added is high, and the similarity between the comprehensive risk bearing capacity value born by the added downstream node and the last downstream node is further detected;
when the similarity value of sim is detected to approach 1, W is represented 1 And W is equal to 2 If the risk value of the downstream node is lower than a second preset value, the downstream node cannot be added; when the similarity of sim is detected to approach 0, W is represented 1 And W is equal to 2 If the risk value of the downstream node is lower than a second preset value, the downstream node can be added;
wherein sim refers to the phaseThe degree of similarity is determined by the degree of similarity,refers to a vector of the first downstream node comprehensive risk bearing capacity values, +>Refers to a vector of the second downstream node comprehensive risk bearing capacity values, |w 1 I is the pointing quantity W 1 Is, |W 2 I is the pointing quantity W 2 Is a mold of (2);
in the process, a formula of the association degree is set, and C is set t It can be understood that the downstream node associated with the upstream node, in other words, the downstream node having cooperation with the upstream node, the set Y is the number of companies (including cooperation or non-cooperation relation) capable of generating a working chain with the upstream node, and the multiplication of Y-1 and Y is set herein, so as to analyze the number of the degree of association between all the cooperation and non-cooperation downstream nodes and the currently set downstream node, namely, the number of times of comparing the degree of association between different downstream nodes; the association degree between different downstream nodes is analyzed through the combination of the formulas, and whether the association can be generated or not is judged;
after determining that the association degree is generated between the downstream nodes, analyzing whether the comprehensive risk bearing capacity value of the downstream node is similar to the last set node or not before adding the downstream node, and analyzing the comprehensive risk bearing capacity value of the next required added node according to the last set downstream node, so that the added node can meet reasonable distribution of risks; the cosine similarity is set to judge the relationship between the downstream nodes, and the downstream nodes display corresponding data, so that the data are integrated for analysis and comparison, and the analysis result has higher precision; there are many methods for analyzing the similarity, for example: if the Euclidean distance is only used for not reflecting the variation trend between the two data, the Euclidean distance is only used for analyzing that the two data have larger difference, and the effect is not as good as a similarity formula used in the method;
compared with the pearson correlation coefficient, the average value of different samples can be subtracted from two vectors, so that the aim of decentralization is achieved, but when the file of the application judges the comprehensive risk bearing capacity value, the comprehensive risk bearing capacity value of the last year is subtracted, so that if the average value of the samples is subtracted again, the average value of the samples is further away from the center, and the achieved precision is not as good as that of the file of the application.
The newly added downstream node distributes part production tasks, when the comprehensive risk bearing capacity value |W of the downstream node is detected x1 -W x2 When |=0, the number of production parts is equally apportioned; when the comprehensive risk tolerance value |W of the downstream node is detected x1 -W x2 |<0, when the downstream node x is detected 2 When the bearing capacity value of the comprehensive risk is larger than a fifth preset value, adding downstream nodes to apportion risks; when the downstream node x is detected 2 When the comprehensive risk bearing capacity value is smaller than the fifth preset value, the number of the parts allocated by the downstream node x2 is larger than that of the downstream node x 1 The number of parts allocated;
after the downstream nodes are added, the values of bearing different comprehensive risk bearing capacities are required to be analyzed, so that the overall risk value is reduced, and the normal operation of the whole supply chain is maintained.
The added downstream node should also acquire the following conditions: any one or any combination of registered capital of the downstream node, liability information of the downstream node, and worker scale involved in part production is obtained.
Example 1: the comprehensive risk bearing capacity value W borne by the downstream node is required to be increased to set the downstream node to share the risk when the W is detected to be larger than a second preset value, and the downstream node is not required to be increased to set the downstream node to share the risk when the W is detected to be smaller than the second preset value;
according to the data display, W Total (S) =5, the capital used by the downstream node in producing the part is P i =3w, all active funds detected for the current downstream node are specifically P i+j =7w, a third preset value of 0.35, a coefficient k of 2.5, w Removing =2.2; standard synthesisThe risk bearing capacity value is 2;
thus, the first and second substrates are bonded together,
W＝W total (S) -a ij *k-W Removing ＝5-2.5-1.2＝1.3；
Wherein W is Total (S) Refers to the total value of total comprehensive risk bearing capacity, a ij Refers to the importance degree, k, of i parts in the rest parts j 1 Refers to risk factor, W Removing Refers to the comprehensive risk bearing capacity value of the last year;
indicating that the risk bearing capacity of the current downstream node is low, a new downstream node needs to be additionally added to share the bearing risk.
Example 2: as shown in FIG. 2, the core commodity is A, A 1 -A 4 As the original downstream node, A 5 Refers to a new downstream node added on the basis of A1.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or 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 may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present application, and the present application is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present application has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (7)
1. A supply chain demand prediction method based on data analysis is characterized by comprising the following steps of: the method specifically comprises the following steps:
acquiring historical data, prejudging the number of required commodity production by a supply chain according to market environment, sales promotion activities and past predicted data, distributing different production numbers to a plurality of downstream nodes according to the predicted production numbers and different parts, judging whether the number is larger than a first preset value according to the difference between the actual sold number of the commodity and the predicted number, and analyzing comprehensive risk bearing values born by the plurality of downstream nodes;
judging whether the comprehensive risk bearing value borne by the downstream nodes is larger than a second preset value or not according to the comprehensive risk bearing values borne by the downstream nodes, adding the downstream nodes to distribute the production quantity of the parts when the comprehensive risk bearing value is larger than the second preset value, modeling according to the production quantity, and reducing the risk value of the independent nodes; when the comprehensive risk bearing value is smaller than a second preset value, no downstream node is required to be added;
the downstream node bears the comprehensive risk bearing value W, when the W is detected to be larger than a second preset value, the downstream node needs to be additionally arranged to share the risk, and when the W is detected to be smaller than the second preset value, the downstream node does not need to be additionally arranged to share the risk;
W＝W total (S) -a ij *k-W Removing ；
Wherein W is Total (S) Refers to the total value of total comprehensive risk bearing capacity, a ij Refers to the importance degree of i parts in the rest parts j, k refers to the risk coefficient, W Removing Refers to the comprehensive risk tolerance value of the last year;
wherein P is i Refers to the funds used in the production of part i, P i+j All active funds of the downstream node;
when P i Occupy P i+j When the probability of (2) is lower than the third preset value, the method indicates thatThe downstream node still has residual active funds to produce other parts besides the current part, which indicates that the risk value of the downstream node is low; when P i Occupy P i+j When the probability of (2) is higher than the third preset value, the downstream node is indicated to have a high risk value, wherein the downstream node comprises the existing funds for producing the current part, and the remaining active funds cannot produce other parts.
2. The method for predicting supply chain demand based on data analysis of claim 1, wherein: when the comprehensive risk bearing value borne by the downstream node is detected to be low, the downstream node is added, wherein the added downstream node meets the following formula:
wherein: h refers to the degree of association, C t The method is characterized in that the method refers to the number of downstream node chains for processing products for upstream nodes, S refers to the association coefficient for producing the same products with the downstream nodes, and Y refers to the number of enterprises of the upstream nodes and the downstream nodes;
when H is lower than a fourth preset value, the association degree between the downstream node and the downstream node to be added is low, when H is higher than the fourth preset value, the association degree between the downstream node and the downstream node to be added is high, and the similarity between the comprehensive risk bearing value born by the added downstream node and the last downstream node is further detected;
when the similarity value of sim is detected to approach 1, W is represented 1 And W is equal to 2 If the risk value of the downstream node is lower than a second preset value, the downstream node cannot be added; when the similarity of sim is detected to approach 0, W is represented 1 And W is equal to 2 Is able to add a downstream node when the risk value of the downstream node is lower than a second preset valueA trip node;
wherein sim refers to the degree of similarity,refers to a vector of first downstream node comprehensive risk bearing values,/->Refers to a vector of the second downstream node comprehensive risk tolerance value, |w 1 I is the pointing quantity W 1 Is, |W 2 I is the pointing quantity W 2 Is a mold of (a).
3. The method for predicting supply chain demand based on data analysis of claim 2, wherein: the newly added downstream node distributes part production tasks, when the comprehensive risk bearing value |W of the downstream node is detected x1 -W x2 When |=0, the number of production parts is equally apportioned; when the comprehensive risk tolerance value |W of the downstream node is detected x1 -W x2 |<When the comprehensive risk bearing value borne by the downstream node x2 is detected to be larger than a fifth preset value, adding the downstream node to apportion the risk; when the comprehensive risk bearing value borne by the downstream node x2 is detected to be smaller than the fifth preset value, the number of the parts allocated by the downstream node x2 is larger than the number of the parts allocated by the downstream node x 1.
4. The method for predicting supply chain demand based on data analysis of claim 2, wherein: the added downstream node should also acquire the following conditions: any one or any combination of registered capital of the downstream node, liability information of the downstream node, and worker scale involved in part production is obtained.
5. A supply chain demand prediction system based on data analysis, the system being implemented using the supply chain demand prediction method based on data analysis as claimed in any one of claims 1 to 4, characterized in that: the system comprises a data preprocessing system and a model building analysis system;
the data preprocessing system is used for analyzing historical predicted data, historical sales data and residual stock quantity data corresponding to the predicted data, extracting characteristic values corresponding to the historical data and judging risk values of the existing data;
the model building analysis system is used for judging comprehensive risk bearing values which can be borne by different downstream node companies according to the risk values of the existing data, and adding downstream nodes to distribute production tasks according to the comprehensive risk bearing values so as to share risks.
6. The data analysis based supply chain demand prediction system of claim 5, wherein: the data preprocessing system comprises a data extraction module and a data analysis module;
the data extraction module is used for acquiring historical sales data and residual stock quantity data, analyzing residual stock data corresponding to the lowest historical sales data and the highest historical sales data, comparing the residual stock data with predicted stock data, and recording and extracting corresponding data with data values smaller than the lowest sales data and corresponding data larger than the highest sales data;
and the data analysis module is used for analyzing that the corresponding data has high risk degree when detecting that the data extracted according with the conditions are present.
7. The data analysis based supply chain demand prediction system of claim 5, wherein: the model building analysis system comprises a supply chain prediction difference analysis module, a risk sharing module, a risk bearing capacity judging module and a production quantity distribution and adjustment module;
the supply chain prediction difference analysis module is used for analyzing whether the difference between the production data required by the supply chain and the actual residual inventory data is larger than a first preset value or not when detecting that the risk value is larger than the standard risk value;
the risk sharing module is used for reducing independent risks born by a single node by arranging a plurality of downstream nodes to share the risks born by the single node;
the risk bearing capacity judging module is used for calling data of the downstream node and analyzing the comprehensive risk bearing value borne by the downstream node;
the production quantity distribution adjusting module distributes production tasks according to risks born by different downstream nodes, so that risks born by one downstream node independently are reduced.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111571430.5A CN114266473B (en) | 2021-12-21 | 2021-12-21 | Supply chain demand prediction system and method based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111571430.5A CN114266473B (en) | 2021-12-21 | 2021-12-21 | Supply chain demand prediction system and method based on data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114266473A CN114266473A (en) | 2022-04-01 |
| CN114266473B true CN114266473B (en) | 2023-12-01 |
Family
ID=80828228
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111571430.5A Active CN114266473B (en) | 2021-12-21 | 2021-12-21 | Supply chain demand prediction system and method based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114266473B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115564497B (en) * | 2022-11-09 | 2023-08-15 | 深圳市鼎山科技有限公司 | Chip supply management system and method based on big data |
| CN116485020B (en) * | 2023-04-18 | 2024-02-23 | 博观创新(上海)大数据科技有限公司 | Supply chain risk identification early warning method, system and medium based on big data |
| CN117252400B (en) * | 2023-11-16 | 2024-02-23 | 天津马上好车信息技术股份有限公司 | Coordination management method, system and application of automobile supply chain |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951982A (en) * | 2014-03-28 | 2015-09-30 | 株式会社日立制作所 | Risk avoidance system |
| CN108898300A (en) * | 2018-06-21 | 2018-11-27 | 南京邮电大学 | The construction method of supply chain network risk cascade model |
| KR20190140296A (en) * | 2018-06-11 | 2019-12-19 | 한국남동발전 주식회사 | Operation system and method for virtual power plant using risk analysis |
| CN113783184A (en) * | 2021-08-19 | 2021-12-10 | 国网四川省电力公司 | Power distribution network multilevel network reconstruction method based on weighting index optimization |
-
2021
- 2021-12-21 CN CN202111571430.5A patent/CN114266473B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951982A (en) * | 2014-03-28 | 2015-09-30 | 株式会社日立制作所 | Risk avoidance system |
| KR20190140296A (en) * | 2018-06-11 | 2019-12-19 | 한국남동발전 주식회사 | Operation system and method for virtual power plant using risk analysis |
| CN108898300A (en) * | 2018-06-21 | 2018-11-27 | 南京邮电大学 | The construction method of supply chain network risk cascade model |
| CN113783184A (en) * | 2021-08-19 | 2021-12-10 | 国网四川省电力公司 | Power distribution network multilevel network reconstruction method based on weighting index optimization |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114266473A (en) | 2022-04-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114266473B (en) | Supply chain demand prediction system and method based on data analysis | |
| US20050096949A1 (en) | Method and system for automatic continuous monitoring and on-demand optimization of business IT infrastructure according to business objectives | |
| CN101771758A (en) | Dynamic determine method for normal fluctuation range of performance index value and device thereof | |
| CN111401642A (en) | Method, device and equipment for automatically adjusting predicted value and storage medium | |
| US20180227435A1 (en) | Telecommunication price-based routing apparatus, system and method | |
| CN114708043B (en) | Method, system, equipment and storage medium for measuring bullwhip effect of supply chain | |
| Kim et al. | Robustness indices and robust prioritization in QFD | |
| CN108549981B (en) | Method for improving service quality of massive parallel business processes | |
| KR102574244B1 (en) | A method and apparatus for generating future demand forecast data based on attention mechanism | |
| Li et al. | On core sorting in RMTS and RMTO systems: A newsvendor framework | |
| Dias | Semiparametric estimation of multi-asset portfolio tail risk | |
| JP2006350883A (en) | Demand prediction value automatic determination system using knowledge database, demand prediction value automatic determination program used therefor, and storage medium storing its program | |
| CN116228375A (en) | Operation management method and device based on cross-border sales system | |
| CN110659930A (en) | Consumption upgrading method and device based on user behaviors, storage medium and equipment | |
| CN113034076B (en) | Logistics carrier object recommendation method and device, electronic equipment and storage medium | |
| Indrawati et al. | Development of supply chain risks interrelationships model using interpretive structural modeling and analytical network process | |
| US20140236667A1 (en) | Estimating, learning, and enhancing project risk | |
| CN109145207B (en) | Information personalized recommendation method and device based on classification index prediction | |
| CN113610627A (en) | Data processing method and device for risk early warning | |
| CN111523083A (en) | Method and device for determining power load declaration data | |
| Zhou et al. | An analytic model for measuring customer's service preferences in manufacturing supply chain | |
| CN116382924B (en) | Recommendation method and device for resource allocation, electronic equipment and storage medium | |
| Konak et al. | A dynamic programming approach for batch sizing in a multi-stage production process with random yields | |
| CN117332917A (en) | Diagnosis method and device for financial products | |
| CN114169861A (en) | Job-hunting risk matching analysis method, system, terminal and medium based on big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |