Warehouse purchase-sale-stock management system and method based on big data analysis

Abstract

The invention discloses a warehouse purchase-sale-stock management system and method based on big data analysis, and relates to the technical field of library purchase-sale-stock management, and the method comprises the steps: collecting historical borrowing data, reader attribute data and time period data in a library business system, and constructing a book circulation feature parameter set based on the historical borrowing data; performing weighted analysis on the book circulation characteristic parameters in combination with the reader attribute data and the time period data to obtain a comprehensive demand index reflecting book demand intensity; constructing a demand prediction model based on the comprehensive demand index, and calculating the predicted demand of each book in different time periods; according to the predicted demand quantity, calculating a corresponding safe stock quantity, and when the current stock quantity is lower than the safe stock quantity, generating a replenishment instruction and a replenishment quantity; and executing the replenishment instruction. According to the invention, the probability of occurrence of empty borrowing of hot books and overstock of low-demand books is effectively reduced.

Description

Technical Field

[0001] This invention relates to the field of library inventory management technology, specifically a warehouse inventory management method based on big data analysis. Background Technology

[0002] With the widespread adoption of library information systems, data on book borrowing, reservations, and inventory can be continuously collected and stored. However, existing book inventory management methods still primarily rely on manual experience or single statistical indicators for decision-making. For example, purchasing and replenishing books based solely on historical borrowing counts or fixed inventory thresholds cannot fully reflect the true demand for books.

[0003] In practical applications, book borrowing demand is influenced by a variety of factors, including borrowing frequency, number of reservations, borrowing period length, and inventory depletion. Existing technologies typically do not provide a unified quantitative model for these multi-dimensional circulation characteristics, resulting in an inaccurate characterization of book demand intensity. This can easily lead to problems such as long-term shortages of popular books and inventory backlogs of books with low demand.

[0004] Furthermore, book borrowing demand exhibits a clear cyclical pattern, fluctuating significantly across different semesters, exam periods, and holidays. Existing management methods largely rely on static rules or post-hoc statistical analysis, lacking the ability to forecast demand based on historical data and hindering timely dynamic adjustments to inventory structure.

[0005] Therefore, existing technologies still have shortcomings in terms of comprehensive assessment of book demand, prediction of demand change trends, and dynamic control of inventory. There is an urgent need for a book inventory management technology solution that can analyze multi-dimensional borrowing data and combine time cycle factors. Summary of the Invention

[0006] The purpose of this invention is to provide a warehouse inventory management method based on big data analysis to solve the problems raised in the prior art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a dynamic inventory management method for library books based on big data analysis, specifically including the following steps: Step S1: Collect historical borrowing data, reader attribute data, and time period data from the library business system, and perform data cleaning, deduplication, and standardization. Step S2: Based on the historical borrowing data, calculate the borrowing frequency, average borrowing duration, number of reservations, and inventory depletion rate of each book within the preset statistical period, and construct a set of book circulation characteristic parameters. Step S3: Combining the reader attribute data and time period data, perform weighted analysis on the book circulation characteristic parameters to obtain a comprehensive demand index that reflects the intensity of book demand; Step S4: Construct a demand forecasting model based on the comprehensive demand index to calculate the predicted demand for each book in different time periods; Step S5: Calculate the corresponding safety stock quantity based on the predicted demand. When the current inventory quantity is lower than the safety stock quantity, generate a replenishment instruction and replenishment quantity. Step S6: Execute the replenishment instruction.

[0008] Furthermore, in step S1, the collection of historical borrowing data, reader attribute data, and time period data from the library's business system specifically includes: It connects to the library business system based on the reserved interface; The historical borrowing data includes the book's unique identifier, borrowing time, return time, number of renewals, reservation records, and inventory change records; The reader attribute data includes the reader's age group, grade, major, and historical borrowing preference tags; The time period data includes natural time information, semester start and end times, exam cycles, and holiday identification information.

[0009] Furthermore, the data cleaning, deduplication, and standardization processes include: Step S1-1: Remove abnormal and duplicate borrowing records from the historical borrowing data; Step S1-2: Fill in the missing fields in the historical borrowing data by interpolating the historical average. Steps S1-3: Normalize the data of different dimensions for unified modeling.

[0010] Furthermore, in step S2, based on the historical borrowing data, the borrowing frequency, average borrowing duration, number of reservations, and inventory depletion rate of each book within a preset statistical period are calculated to construct a set of book circulation characteristic parameters. These parameters are then weighted and analyzed in conjunction with the reader attribute data and time period data to obtain a comprehensive demand index reflecting the intensity of book demand. Specifically: Step S2-1: Within a preset statistical period T, calculate circulation characteristic parameters for each book and book category; the circulation characteristic parameters include the total number of times a book is borrowed f within the preset statistical period T, the average duration t of each borrowing, the number of readers who reserve a book r, and the inventory depletion rate b. Step S2-2: Based on the aforementioned circulation characteristic parameters, uniformly characterize the demand intensity of books and construct a comprehensive demand index D. The calculation formula is as follows: D=α*f+β*r+γ*(1 / t)+δ*b; Wherein: α, β, γ and δ are the weighting coefficients of borrowing frequency, average borrowing duration, number of reservations and inventory depletion rate, respectively, used to adjust the influence ratio of different circulation characteristic parameters in the comprehensive demand index; the weighting coefficients are normalized to satisfy α+β+γ+δ=1.

[0011] Preferably, the inventory depletion rate b is the ratio of the cumulative duration during which the book inventory quantity is zero within a preset statistical period T to the preset statistical period T.

[0012] Preferably, the method for determining the weighting coefficients α, β, γ, and δ is as follows: Step 1: Obtain N sets of historical borrowing data within the preset statistical period T as samples for correlation analysis. Statistically obtain all books within the preset statistical period T. Specifically, for any book a, calculate the total borrowing volume y and the total number of times book a was borrowed f within the preset statistical period T. a The average duration t of each borrowing of book a a The number of readers who reserved book a, r a And the inventory clearance rate of book a and book b a ; Step 2: Obtain the total borrowing volume of book a, the total number of times book a was borrowed, the average duration of each borrowing of book a, the number of readers who reserved book a, and the inventory clearance rate of book a from each of the N sets of correlation analysis samples; where the total borrowing volume of books in the N sets of correlation analysis samples is denoted as the total borrowing volume sequence Y=(y1,...,y n ,...,y N ); sequentially obtain the borrowing frequency sequence Fa=(f) from N sets of correlation analysis samples. a1 ,...,f an ,...,f aN The sequence of the number of readers who reserved book a is Ra = (r a1 ,...,r an ,...,r aN ); the reciprocal sequence of borrowing duration T'a=(t' a1 ,...,t' an ,...,t' aN ); Inventory borrowing rate sequence Ba=(b a1 ,...,b an ,...,b aN ); where y1,...,y n ,...,yN f represents the total number of books borrowed for the 1st, ..., nth, ..., Nth correlation analysis samples, respectively; a1 ,...,f an ,...,f aN Let r represent the total number of times book a was borrowed in the 1st, ..., nth, ..., Nth correlation analysis samples, respectively; a1 ,...,r an ,...,r aN Let t' represent the number of readers who reserved book a in the 1st, ..., nth, ..., Nth correlation analysis samples, respectively; a1 ,...,t' an ,...,t' aN Let a represent the reciprocal of the average borrowing duration of each book in the 1st, ..., nth, ..., Nth correlation analysis samples; b represent the reciprocal of the average borrowing duration of each book in the 1st, ..., Nth correlation analysis samples; a1 ,...,b an ,...,b aN Let represent the inventory clearance rate of book a in the 1st, ..., nth, ..., Nth correlation analysis samples, respectively; Step 3: Based on the above sequences Y, Fa, Ra, T'a, and Ba, calculate the Pearson correlation coefficients between sequences Fa, Ra, T'a, and Ba and sequence Y, denoted as ρ(Fa,Y), ρ(Ra,Y), ρ(T'a,Y), and ρ(Ba,Y), respectively. Wherein, ρ(Fa,Y) represents the Pearson correlation coefficient between the borrowing frequency of book a and the total borrowing volume; ρ(Ra,Y) represents the Pearson correlation coefficient between the number of readers who reserved book a and the total borrowing volume; ρ(T'a,Y) represents the Pearson correlation coefficient between the reciprocal of the borrowing duration of each instance of book a and the total borrowing volume; and ρ(Ba,Y) represents the Pearson correlation coefficient between the inventory depletion rate of book a and the total borrowing volume. Step 4: Based on the obtained Pearson correlation coefficient, standardize the data. Use the standardized ρ(Fa,Y) value as the weighting coefficient for the borrowing frequency of book a; use the standardized ρ(Ra,Y) value as the weighting coefficient for the average borrowing duration of book a; use the standardized ρ(T'a,Y) value as the weighting coefficient for the number of reservations for book a; and use the standardized ρ(Ba,Y) value as the weighting coefficient for the inventory depletion rate of book a.

[0013] Furthermore, in step S4, the step of constructing a demand forecasting model based on the comprehensive demand index to calculate the predicted demand for each book in different time periods specifically involves: Step S4-1: Based on the comprehensive demand index D, D is used as a unified quantitative indicator to represent the intensity of book borrowing demand, and a historical demand index sequence is constructed in chronological order: D*={D1,…,Dm,...,DM}; where D1,…,Dm,...,DM represent the comprehensive demand index of the corresponding book in the 1st,...,m,...,Mth preset statistical period T, respectively. Step S4-2: Based on the moving average forecast, input the historical demand index sequence D*={D1,…,Dm,...,DM}, and take the average of the comprehensive demand index over the most recent k statistical periods as the basis for forecasting the next period. It is characterized as follows: Where k represents the sliding window length, used to balance the stationarity and sensitivity of the prediction results; k is a positive integer; Step S4-3: Determine the periodic adjustment factor C based on the percentage change in the average demand index over the same historical period, specifically as follows: ;in, This represents the average composite demand index within the same historical period of the same semester and holiday type. This represents the average composite demand index over all statistical periods; Step S4-4: Introduce a periodic correction factor C to predict the composite demand index for the next statistical period. Represented as: ; Furthermore, in step S5, based on the predicted demand, the corresponding safety stock quantity is calculated. When the current inventory quantity is lower than the safety stock quantity, a replenishment instruction and replenishment quantity are generated, specifically as follows: Step S5-1: Based on the predicted value of the comprehensive demand index Converted to the predicted borrowing demand μ, it is represented as: Where α and β are the conversion slope and intercept determined by fitting the relationship between the historical comprehensive demand index and the actual borrowing volume; Step S5-2: Calculate the corresponding safety stock quantity S based on the statistical distribution, which is represented as: S=μ+h*σ; where σ is the standard deviation of the borrowing demand corresponding to the comprehensive demand index of books within the statistical period; h represents the safety factor; used to control the level of inventory risk.

[0014] Step S5-3: If the current inventory quantity is lower than the safety stock quantity S, generate a replenishment instruction and replenishment quantity.

[0015] Furthermore, in step S6, executing the replenishment instruction also includes: After a statistical period ends, the historical borrowing data is stored and updated, and the fitting relationship between the historical comprehensive demand index and the actual borrowing volume is refitted, updating the conversion slope and intercept.

[0016] A warehouse inventory management system based on big data analytics includes a data acquisition and interface access module, a data preprocessing module, a book circulation feature extraction module, a weight adaptive calculation module, a comprehensive demand index calculation module, a demand forecasting and cycle correction module, and a decision execution and data update module. The data acquisition and interface access module is used to connect with the library business system based on the reserved interface to collect historical borrowing data, reader attribute data and time period data from the library business system. The data preprocessing module is used for data cleaning, deduplication, and standardization. The book circulation feature extraction module is used to calculate the borrowing frequency, average borrowing duration, number of reservations, and inventory depletion rate of each book within a preset statistical period based on historical borrowing data, and to construct a set of book circulation feature parameters. The weight adaptive calculation module is used to calculate the weights of circulation characteristic parameters based on the Pearson correlation coefficient method; The comprehensive demand index calculation module is used to combine the reader attribute data and time period data to perform weighted analysis on the book circulation characteristic parameters to obtain a comprehensive demand index that reflects the intensity of book demand. The demand forecasting and cycle correction module is used to construct a demand forecasting model based on the comprehensive demand index and calculate the predicted demand for each book in different time periods. The decision execution is used to calculate the corresponding safety stock quantity based on the predicted demand, and when the current inventory quantity is lower than the safety stock quantity, generate a replenishment instruction and replenishment quantity. The data update module is used to execute the replenishment instruction and update the historical borrowing data.

[0017] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention comprehensively models multi-dimensional circulation characteristics such as book borrowing frequency, number of reservations, borrowing duration, and inventory depletion rate to construct a unified comprehensive demand index, thereby achieving a quantitative representation of the intensity of real book demand. Furthermore, it adaptively allocates weights based on the statistical correlation between each circulation characteristic parameter and the actual borrowing demand, reducing subjective bias caused by manual experience-based settings. Simultaneously, it constructs a historical time series using the comprehensive demand index and introduces periodic correction factors such as semesters, exam cycles, and holidays to predict future trends in book demand, thus providing a basis for inventory replenishment and early warning threshold setting. This enables dynamic control of book inventory management, effectively reducing the probability of popular books being depleted and low-demand books accumulating inventory. Moreover, this method can be implemented primarily based on borrowing and reservation data in existing book management systems, exhibiting good engineering feasibility and applicability for widespread adoption. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating a warehouse inventory management method based on big data analysis according to the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Example: Figure 1 As shown, this invention provides a technical solution: a method for dynamic inventory management of library books based on big data analysis, specifically including the following steps: Step S1: Collect historical borrowing data, reader attribute data, and time period data from the library business system, and perform data cleaning, deduplication, and standardization. Step S2: Based on the historical borrowing data, calculate the borrowing frequency, average borrowing duration, number of reservations, and inventory depletion rate of each book within the preset statistical period, and construct a set of book circulation characteristic parameters. Step S3: Combining the reader attribute data and time period data, perform weighted analysis on the book circulation characteristic parameters to obtain a comprehensive demand index that reflects the intensity of book demand; Step S4: Construct a demand forecasting model based on the comprehensive demand index to calculate the predicted demand for each book in different time periods. Step S5: Calculate the corresponding safety stock quantity based on the predicted demand. When the current inventory quantity is lower than the safety stock quantity, generate a replenishment instruction and replenishment quantity. Step S6: Execute the replenishment instruction.

[0021] Furthermore, in step S1, historical borrowing data, reader attribute data, and time period data are collected from the library's business system, specifically as follows: It connects to the library business system based on the reserved interface; Historical borrowing data includes the book's unique identifier, borrowing time, return time, number of renewals, reservation records, and inventory change records; Reader attribute data includes readers' age group, grade, major, and historical borrowing preference tags; The time period data includes natural time information, semester start and end times, exam cycles, and holiday identification information.

[0022] Further, data cleaning, deduplication, and standardization processes are performed, including: Step S1-1: Remove abnormal and duplicate borrowing records from the historical borrowing data; Step S1-2: Fill in the missing fields in the historical borrowing data by interpolating the historical average. Steps S1-3: Normalize the data of different dimensions for unified modeling.

[0023] Furthermore, in step S2, based on historical borrowing data, the borrowing frequency, average borrowing duration, number of reservations, and inventory depletion rate of each book within a preset statistical period are calculated to construct a set of book circulation characteristic parameters. These parameters are then weighted and analyzed in conjunction with the reader attribute data and time period data to obtain a comprehensive demand index reflecting the intensity of book demand. Specifically: Step S2-1: Within a preset statistical period T, calculate circulation characteristic parameters for each book and book category; the circulation characteristic parameters include the total number of times a book is borrowed f within the preset statistical period T, the average duration of each borrowing t, the number of readers who reserve a book r, and the inventory depletion rate b. Step S2-2: Using the aforementioned circulation characteristic parameters as a basis, uniformly characterize the demand intensity of books and construct a comprehensive demand index D. The calculation formula is as follows: D = α*f + β*r + γ*(1 / t) + δ*b; Wherein: α, β, γ and δ are the weighting coefficients of borrowing frequency, average borrowing duration, number of reservations and inventory depletion rate, respectively, used to adjust the influence ratio of different circulation characteristic parameters in the comprehensive demand index; the weighting coefficients are normalized to satisfy α+β+γ+δ=1.

[0024] It should be noted that the comprehensive demand index is used to measure the actual demand intensity for books in the current statistical period and serves as an input variable for subsequent demand forecasting models. Preferably, the inventory depletion rate b is the ratio of the cumulative duration during which the book inventory quantity is zero within a preset statistical period T to the preset statistical period T.

[0025] Since the comprehensive demand index for different books and book categories actually reflects whether the book is needed in a timely manner, for example, relying solely on borrowing frequency f easily overlooks pre-booking demand; ignoring inventory depletion rate b fails to reflect the implicit demand of "long-term shortages"; and without considering borrowing duration t, it is difficult to identify textbooks that have "slow turnover but strong demand." The weighting mechanism achieves a balanced expression of multi-dimensional demand signals. Therefore, weighting in the weighted analysis process is crucial. By adjusting the weights, separate rules for each book category can be avoided. This application uses an analysis method based on changes at different time points for weighting.

[0026] Preferably, the method for determining the weighting coefficients α, β, γ, and δ is as follows: Step 1: Obtain N sets of historical borrowing data within a preset statistical period T as samples for correlation analysis. Statistically obtain all books within the preset statistical period T. For any book a, calculate the total borrowing volume y and the total number of times book a was borrowed f within the preset statistical period T. a The average duration t of each borrowing of book a a The number of readers who reserved book a, r a And the inventory clearance rate of book a and book b a ; Step 2: Obtain the total borrowing volume of book a, the total number of times book a was borrowed, the average duration of each borrowing of book a, the number of readers who reserved book a, and the inventory clearance rate of book a from each of the N sets of correlation analysis samples; where the total borrowing volume of books in the N sets of correlation analysis samples is denoted as the total borrowing volume sequence Y=(y1,...,y n ,...,y N ); sequentially obtain the borrowing frequency sequence Fa=(f) from N sets of correlation analysis samples. a1 ,...,f an ,...,f aN The sequence of the number of readers who reserved book a is Ra = (r a1 ,...,ran ,...,r aN ); the reciprocal sequence of borrowing duration T'a=(t' a1 ,...,t' an ,...,t' aN ); Inventory borrowing rate sequence Ba=(b a1 ,...,b an ,...,b aN ); where y1,...,y n ,...,y N f represents the total number of books borrowed for the 1st, ..., nth, ..., Nth correlation analysis samples, respectively; a1 ,...,f an ,...,f aN Let r represent the total number of times book a was borrowed in the 1st, ..., nth, ..., Nth correlation analysis samples, respectively; a1 ,...,r an ,...,r aN Let t' represent the number of readers who reserved book a in the 1st, ..., nth, ..., Nth correlation analysis samples, respectively; a1 ,...,t' an ,...,t' aN Let a represent the reciprocal of the average borrowing duration of each book in the 1st, ..., nth, ..., Nth correlation analysis samples; b represent the reciprocal of the average borrowing duration of each book in the 1st, ..., Nth correlation analysis samples; a1 ,...,b an ,...,b aN Let represent the inventory clearance rate of book a in the 1st, ..., nth, ..., Nth correlation analysis samples, respectively; Step 3: Based on the above sequences Y, Fa, Ra, T'a, and Ba, calculate the Pearson correlation coefficients between sequences Fa, Ra, T'a, and Ba and sequence Y, denoted as ρ(Fa,Y), ρ(Ra,Y), ρ(T'a,Y), and ρ(Ba,Y), respectively. Wherein, ρ(Fa,Y) represents the Pearson correlation coefficient between the borrowing frequency of book a and the total borrowing volume; ρ(Ra,Y) represents the Pearson correlation coefficient between the number of readers who reserved book a and the total borrowing volume; ρ(T'a,Y) represents the Pearson correlation coefficient between the reciprocal of the borrowing duration of each instance of book a and the total borrowing volume; and ρ(Ba,Y) represents the Pearson correlation coefficient between the inventory depletion rate of book a and the total borrowing volume. Step 4: Based on the obtained Pearson correlation coefficient, standardize the data. Use the standardized ρ(Fa,Y) value as the weighting coefficient for the borrowing frequency of book a; use the standardized ρ(Ra,Y) value as the weighting coefficient for the average borrowing duration of book a; use the standardized ρ(T'a,Y) value as the weighting coefficient for the number of reservations for book a; and use the standardized ρ(Ba,Y) value as the weighting coefficient for the inventory depletion rate of book a.

[0027] It should be noted that the Pierce correlation coefficient method is an existing technology, commonly used in the calculation of sequence correlation, with a value of [-1, 1]; it can represent positive correlation and negative correlation. In this application, the correlation between each parameter and the total number of borrowers is used to characterize the weight factor, avoiding the problem of abnormal demand caused by insufficient experience in weight allocation, and improving the stability of weight allocation. It is important to note that before calculating and analyzing the Pearson correlation coefficient, the data must be normalized to eliminate the influence of dimensions. The normalization method can be Max-Min or Z-score, and there is no restriction here.

[0028] Furthermore, in step S4, a demand forecasting model is constructed based on the comprehensive demand index to calculate the predicted demand for each book in different time periods, specifically as follows: Step S4-1: Based on the comprehensive demand index D, D is used as a unified quantitative indicator to represent the intensity of book borrowing demand, and a historical demand index sequence is constructed in chronological order: D*={D1,…,Dm,...,DM}; where D1,…,Dm,...,DM represent the comprehensive demand index of the corresponding book in the 1st,...,m,...,Mth preset statistical period T, respectively. By constructing a historical demand index sequence in chronological order, the originally discrete borrowing behavior data is transformed into continuous time series data, providing a foundation for subsequent analysis of demand change trends.

[0029] Step S4-2: Based on the moving average forecast, input the historical demand index sequence D*={D1,…,Dm,...,DM}, and take the average of the comprehensive demand index over the most recent k statistical periods as the basis for forecasting the next period. It is characterized as follows: Where k represents the sliding window length, used to balance the stationarity and sensitivity of the prediction results; k is a positive integer; Since book borrowing demand is significantly affected by factors such as semester schedules, exam cycles, and holidays, predictions based solely on historical trends may not accurately reflect sudden changes in demand. Therefore, a periodic correction factor C is introduced into the prediction process.

[0030] Step S4-3: Determine the periodic adjustment factor C based on the percentage change in the average demand index over the same historical period, specifically as follows: ;in, This represents the average composite demand index within the same historical period of the same semester and holiday type. This represents the average composite demand index over all statistical periods; Step S4-4: Introduce a periodic correction factor C to predict the composite demand index for the next statistical period. Represented as: ; Among them, the forecast value of the composite demand index for the next statistical period It also reflects the impact of historical demand trends and cyclical changes.

[0031] It should be noted that the periodic correction factor C can be set according to the actual situation. Specifically, when the prediction period is at the beginning of the semester, during the exam review period, or during the intensive teaching period, C>1 is set to amplify the basic prediction value; when the prediction period is during winter and summer vacations or non-peak teaching periods, C≤1 is set to suppress demand expectations; when it is in a regular teaching period, C takes a value close to 1. Furthermore, in step S5, the corresponding safety stock quantity is calculated based on the predicted demand. When the current inventory quantity is lower than the safety stock quantity, a replenishment instruction and replenishment quantity are generated, specifically as follows: Step S5-1: Based on the predicted value of the comprehensive demand index Converted to the predicted borrowing demand μ, it is represented as: Where α and β are the conversion slope and intercept determined by fitting the relationship between the historical comprehensive demand index and the actual borrowing volume; It should be noted that since the comprehensive demand index D is a normalized and weighted index and does not directly correspond to the specific number of borrowings, the predicted comprehensive demand index needs to be converted into the predicted borrowing demand μ. In this application, the solution is obtained by linear fitting, but it can also be fitted by nonlinear or polynomial methods, and no further restrictions are imposed here.

[0032] Step S5-2: Calculate the corresponding safety stock quantity S based on the statistical distribution, which is represented as: S=μ+h*σ; where σ is the standard deviation of the borrowing demand corresponding to the comprehensive demand index of books within the statistical period; h represents the safety factor; used to control the level of inventory risk.

[0033] Step S5-3: If the current inventory quantity is lower than the safety stock quantity S, generate a replenishment instruction and replenishment quantity.

[0034] The replenishment quantity is the difference between the safety stock quantity S and the current inventory quantity.

[0035] Furthermore, in step S6, executing the replenishment instruction also includes: After a statistical period ends, the historical borrowing data is stored and updated, and the fitting relationship between the historical comprehensive demand index and the actual borrowing volume is refitted, updating the conversion slope and intercept.

[0036] For those skilled in the art, it is obvious that this invention is not limited to the field of school libraries, but can also be applied to other areas related to book lending and document lending, all of which fall within the scope of protection of this patent. For example, in the field of inventory management of materials and archives in hospital clinical departments, a demand prediction model can be formed by using parameters such as borrowing frequency, average borrowing duration, number of reservations, and inventory depletion rate within a certain preset statistical period to form inventory management.

[0037] A warehouse inventory management system based on big data analytics includes a data acquisition and interface access module, a data preprocessing module, a book circulation feature extraction module, a weight adaptive calculation module, a comprehensive demand index calculation module, a demand forecasting and cycle correction module, and a decision execution and data update module. The data acquisition and interface access module is used to connect with the library business system based on the reserved interface to collect historical borrowing data, reader attribute data and time period data from the library business system; The data preprocessing module is used for data cleaning, deduplication, and standardization. The book circulation feature extraction module is used to calculate the borrowing frequency, average borrowing duration, number of reservations, and inventory depletion rate of each book within a preset statistical period based on historical borrowing data, and to construct a set of book circulation feature parameters. The weight adaptive calculation module is used to calculate the weights of circulation characteristic parameters based on the Pearson correlation coefficient method; The comprehensive demand index calculation module is used to combine reader attribute data and time period data to perform weighted analysis on the characteristic parameters of book circulation, and obtain a comprehensive demand index that reflects the intensity of book demand. The demand forecasting and cycle correction module is used to build a demand forecasting model based on the comprehensive demand index and calculate the predicted demand for each book in different time periods. The decision execution function calculates the corresponding safety stock quantity based on the predicted demand. When the current inventory quantity is lower than the safety stock quantity, it generates a replenishment instruction and the replenishment quantity. The data update module is used to execute replenishment orders and update historical borrowing data.

[0038] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A warehouse inventory management method based on big data analysis, characterized in that: Specifically, the steps include the following: Step S1: Collect historical borrowing data, reader attribute data, and time period data from the library business system, and perform data cleaning, deduplication, and standardization. Step S2: Based on the historical borrowing data, calculate the borrowing frequency, average borrowing duration, number of reservations, and inventory depletion rate of each book within the preset statistical period, and construct a set of book circulation characteristic parameters. Step S3: Combining the reader attribute data and time period data, perform weighted analysis on the book circulation characteristic parameters to obtain a comprehensive demand index that reflects the intensity of book demand; Step S4: Construct a demand forecasting model based on the comprehensive demand index to calculate the predicted demand for each book in different time periods; Step S5: Calculate the corresponding safety stock quantity based on the predicted demand. When the current inventory quantity is lower than the safety stock quantity, generate a replenishment instruction and replenishment quantity. Step S6: Execute the replenishment instruction.

2. The warehouse inventory management method based on big data analysis according to claim 1, characterized in that: In step S1, the collection of historical borrowing data, reader attribute data, and time period data from the library's business system specifically includes: It connects to the library business system based on the reserved interface; The historical borrowing data includes the book's unique identifier, borrowing time, return time, number of renewals, reservation records, and inventory change records; The reader attribute data includes the reader's age group, grade, major, and historical borrowing preference tags; The time period data includes natural time information, semester start and end times, exam cycles, and holiday identification information.

3. The warehouse inventory management method based on big data analysis according to claim 2, characterized in that: The data cleaning, deduplication, and standardization processes include: Step S1-1: Remove abnormal and duplicate borrowing records from the historical borrowing data; Step S1-2: Fill in the missing fields in the historical borrowing data by interpolating the historical average. Steps S1-3: Normalize the data of different dimensions for unified modeling.

4. The warehouse inventory management method based on big data analysis according to claim 3, characterized in that: In step S2, based on the historical borrowing data, the borrowing frequency, average borrowing duration, number of reservations, and inventory depletion rate of each book within a preset statistical period are calculated to construct a set of book circulation characteristic parameters. These parameters are then weighted and analyzed in conjunction with the reader attribute data and time period data to obtain a comprehensive demand index reflecting the intensity of book demand. Specifically: Step S2-1: Within a preset statistical period T, calculate circulation characteristic parameters for each book and book category; the circulation characteristic parameters include the total number of times a book is borrowed f within the preset statistical period T, the average duration t of each borrowing, the number of readers who reserve a book r, and the inventory depletion rate b. Step S2-2: Based on the aforementioned circulation characteristic parameters, uniformly characterize the demand intensity of books and construct a comprehensive demand index D. The calculation formula is as follows: D=α*f+β*r+γ*(1 / t)+δ*b; Wherein, α, β, γ and δ are the weighting coefficients of borrowing frequency, average borrowing duration, number of reservations and inventory depletion rate, respectively, used to adjust the influence ratio of different circulation characteristic parameters in the comprehensive demand index; the weighting coefficients are normalized to satisfy α+β+γ+δ=1.

5. The warehouse inventory management method based on big data analysis according to claim 4, characterized in that: The method for determining the weighting coefficients α, β, γ, and δ is as follows: Step 1: Obtain N sets of historical borrowing data within the preset statistical period T as samples for correlation analysis. Statistically obtain all books within the preset statistical period T. Specifically, for any book a, calculate the total borrowing volume y and the total number of times book a was borrowed f within the preset statistical period T. a The average duration t of each borrowing of book a a The number of readers who reserved book a, r a And the inventory clearance rate of book a and book b a ; Step 2: Obtain the total borrowing volume of book a, the total number of times book a was borrowed, the average duration of each borrowing of book a, the number of readers who reserved book a, and the inventory clearance rate of book a from each of the N sets of correlation analysis samples; where the total borrowing volume of books in the N sets of correlation analysis samples is denoted as the total borrowing volume sequence Y=(y1,...,y n ,...,y N ); sequentially obtain the borrowing frequency sequence Fa=(f) from N sets of correlation analysis samples. a1 ,...,f an ,...,f aN The sequence of the number of readers who reserved book a is Ra = (r a1 ,...,r an ,...,r aN ); the reciprocal sequence of borrowing duration T'a=(t' a1 ,...,t' an ,...,t' aN ); Inventory borrowing rate sequence Ba=(b a1 ,...,b an ,...,b aN ); where y1,...,y n ,...,y N f represents the total number of books borrowed for the 1st, ..., nth, ..., Nth correlation analysis samples, respectively; a1 ,...,f an ,...,f aN Let r represent the total number of times book a was borrowed in the 1st, ..., nth, ..., Nth correlation analysis samples, respectively; a1 ,...,r an ,...,r aN Let t' represent the number of readers who reserved book a in the 1st, ..., nth, ..., Nth correlation analysis samples, respectively; a1 ,...,t' an ,...,t' aN Let a represent the reciprocal of the average borrowing duration of each book in the 1st, ..., nth, ..., Nth correlation analysis samples; b represent the reciprocal of the average borrowing duration of each book in the 1st, ..., Nth correlation analysis samples; a1 ,...,b an ,...,b aN Let represent the inventory clearance rate of book a in the 1st, ..., nth, ..., Nth correlation analysis samples, respectively; Step 3: Based on the above sequences Y, Fa, Ra, T'a, and Ba, calculate the Pearson correlation coefficients between sequences Fa, Ra, T'a, and Ba and sequence Y, denoted as ρ(Fa,Y), ρ(Ra,Y), ρ(T'a,Y), and ρ(Ba,Y), respectively. Wherein, ρ(Fa,Y) represents the Pearson correlation coefficient between the borrowing frequency of book a and the total borrowing volume; ρ(Ra,Y) represents the Pearson correlation coefficient between the number of readers who reserved book a and the total borrowing volume; ρ(T'a,Y) represents the Pearson correlation coefficient between the reciprocal of the borrowing duration of each instance of book a and the total borrowing volume; and ρ(Ba,Y) represents the Pearson correlation coefficient between the inventory depletion rate of book a and the total borrowing volume. Step 4: Based on the obtained Pearson correlation coefficient, standardize the data. Use the standardized ρ(Fa,Y) value as the weighting coefficient for the borrowing frequency of book a; use the standardized ρ(Ra,Y) value as the weighting coefficient for the average borrowing duration of book a; use the standardized ρ(T'a,Y) value as the weighting coefficient for the number of reservations for book a; and use the standardized ρ(Ba,Y) value as the weighting coefficient for the inventory depletion rate of book a.

6. The warehouse inventory management method based on big data analysis according to claim 4, characterized in that: The inventory depletion rate b is the ratio of the cumulative duration during which the book inventory quantity is zero within a preset statistical period T to the preset statistical period T.

7. A warehouse inventory management method based on big data analysis according to claim 6, characterized in that: In step S4, the demand forecasting model is constructed based on the comprehensive demand index to calculate the predicted demand for each book in different time periods, specifically as follows: Step S4-1: Based on the comprehensive demand index D, D is used as a unified quantitative indicator to represent the intensity of book borrowing demand, and a historical demand index sequence is constructed in chronological order: D*={D1,…,Dm,...,DM}; where D1,…,Dm,...,DM represent the comprehensive demand index of the corresponding book in the 1st,...,m,...,Mth preset statistical period T, respectively. Step S4-2: Based on the moving average forecast, input the historical demand index sequence D*={D1,…,Dm,...,DM}, and take the average of the comprehensive demand index over the most recent k statistical periods as the basis for forecasting the next period. It is characterized as follows: Where k represents the sliding window length, and k is a positive integer; Step S4-3: Determine the periodic adjustment factor C based on the percentage change in the average demand index over the same historical period, specifically as follows: ;in, This represents the average composite demand index within the same historical period of the same semester and holiday type. This represents the average composite demand index over all statistical periods; Step S4-4: Introduce a periodic correction factor C to predict the composite demand index for the next statistical period. Represented as: .

8. The warehouse inventory management method based on big data analysis according to claim 7, characterized in that: In step S5, based on the predicted demand, the corresponding safety stock quantity is calculated. When the current inventory quantity is lower than the safety stock quantity, a replenishment instruction and replenishment quantity are generated, specifically as follows: Step S5-1: Based on the predicted value of the comprehensive demand index Converted to the predicted borrowing demand μ, it is represented as: Where α and β are the conversion slope and intercept determined by fitting the relationship between the historical comprehensive demand index and the actual borrowing volume; Step S5-2: Calculate the corresponding safety stock quantity S based on the statistical distribution, which is represented as: S=μ+h*σ; where σ is the standard deviation of the borrowing demand corresponding to the comprehensive demand index of books within the statistical period; h represents the safety factor; Step S5-3: If the current inventory quantity is lower than the safety stock quantity S, generate a replenishment instruction and replenishment quantity.

9. A warehouse inventory management method based on big data analysis according to claim 8, characterized in that: In step S6, executing the replenishment instruction further includes: After a statistical period ends, the historical borrowing data is stored and updated, and the fitting relationship between the historical comprehensive demand index and the actual borrowing volume is refitted, updating the conversion slope and intercept.

10. A warehouse inventory management system based on big data analytics, employing the warehouse inventory management method based on big data analytics as described in any one of claims 1-9, characterized in that: It includes a data acquisition and interface access module, a data preprocessing module, a book circulation feature extraction module, a weight adaptive calculation module, a comprehensive demand index calculation module, a demand forecasting and cycle correction module, and a decision execution and data update module; The data acquisition and interface access module is used to connect with the library business system based on the reserved interface to collect historical borrowing data, reader attribute data and time period data from the library business system. The data preprocessing module is used for data cleaning, deduplication, and standardization. The book circulation feature extraction module is used to calculate the borrowing frequency, average borrowing duration, number of reservations, and inventory depletion rate of each book within a preset statistical period based on historical borrowing data, and to construct a set of book circulation feature parameters. The weight adaptive calculation module is used to calculate the weights of circulation characteristic parameters based on the Pearson correlation coefficient method; The comprehensive demand index calculation module is used to combine the reader attribute data and time period data to perform weighted analysis on the book circulation characteristic parameters to obtain a comprehensive demand index that reflects the intensity of book demand. The demand forecasting and cycle correction module is used to construct a demand forecasting model based on the comprehensive demand index and calculate the predicted demand for each book in different time periods. The decision execution is used to calculate the corresponding safety stock quantity based on the predicted demand, and when the current inventory quantity is lower than the safety stock quantity, generate a replenishment instruction and replenishment quantity. The data update module is used to execute the replenishment instruction and update the historical borrowing data.

Images