Adaptive price inquiry and comparison service optimization management system based on artificial intelligence

Abstract

The present invention discloses an adaptive price inquiry and comparison service optimization management system based on artificial intelligence, which belongs to the technical field of price inquiry and comparison, and specifically comprises: the initial duration of a collection cycle, collecting the market price of any item every collection cycle, generating a market price sequence every n collection cycles, and obtaining a market price index; calculating an adjustment coefficient α of the collection cycle according to the market price index, calculating the adjustment coefficient α according to the market price index every n collection cycles, and adjusting the duration of the next n collection cycles according to the adjustment coefficient α; when the market price of the item collected in any collection cycle is lower than A% of the current purchase price of the item, A is a set value, and a purchase price abnormality prompt is issued; the present invention can effectively cope with market price fluctuations.

Description

Technical Field

[0001] The present invention relates to the technical field of price inquiry and comparison, and in particular to an artificial intelligence-based adaptive price inquiry and comparison service optimization management system. Background Art

[0002] In the modern business environment, effective procurement management is the key to reducing costs and improving competitiveness. Traditional price comparison services rely on manual operations and experience judgment, which is not only time-consuming and labor-intensive, but also difficult to respond to market changes in real time, resulting in procurement decisions often lagging behind market price fluctuations, increasing procurement costs and risks for enterprises.

[0003] With the development of information technology, especially the application of artificial intelligence technology, it is possible to solve the limitations of traditional price comparison services. However, after signing a supply contract with a supplier, existing enterprises generally do not pay too much attention to the price of the next item. Most of them collect market price data in a fixed period, and fail to fully consider the market dynamics and seasonal fluctuations, resulting in the collected data being unable to reflect the current market situation in a timely manner. When the price of an item changes rapidly, it is impossible to change the supply chain strategy in time according to the real-time market price situation, resulting in a loss of corporate benefits. Summary of the invention

[0004] The purpose of the present invention is to provide an adaptive price inquiry and comparison service optimization management system based on artificial intelligence to solve the following technical problems:

[0005] After existing companies sign a supply contract with a supplier, they generally do not pay too much attention to the subsequent prices of the goods. Most of them collect market price data in a fixed period, fail to fully consider market dynamics and seasonal fluctuations, and are unable to change supply chain strategies in a timely manner based on real-time market price conditions.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] The adaptive price inquiry and comparison service optimization management system based on artificial intelligence includes:

[0008] The information collection module is used to set the initial duration of the collection cycle, collect the market price of any item every collection cycle, generate a market price sequence every n collection cycles, obtain the most recent market price P in the market price sequence, and the proportion B of the number of items in the market price sequence that are lower than the purchase price P0 of the item in the sequence, and draw a line coordinate graph of the market price changing over time, and represent the line with a piecewise function f(t), t∈[1,n], connect the first and last coordinate points of the line graph, and represent the obtained connection line with a straight line function F(t);

[0009] The information processing module is used to calculate the adjustment coefficient α of the collection period according to the market price index, wherein the market price index includes the latest market price P, the ratio B, the integral of the piecewise function f(t) and the integral of the linear function F(x), and the adjustment coefficient α of the collection period is calculated by the following formula:

[0010] ;

[0011] Where β represents the correction coefficient;

[0012] The cycle adjustment module is used to calculate the adjustment coefficient α according to the market price index every n collection cycles, and mark the duration of the current collection cycle as T 原 , then adjust the duration T of the next n acquisition cycles according to the adjustment coefficient α 新 =T 原 α;

[0013] The price comparison prompt module is used to issue a purchase price abnormality prompt when the market price of an item collected in any collection period is lower than A% of the current purchase price of the item, where A is a set value.

[0014] As a further solution of the present invention: in the information collection module, the market price is the lowest value among the prices of items from all market data sources, and the data sources include online shopping malls, physical store prices, and transaction records.

[0015] As a further solution of the present invention: the information collection module also includes a data filtering unit, which is used to interpolate and replace abnormal values ​​in the market price sequence, and the abnormal values ​​are values ​​that differ too much from the average value of the market price sequence.

[0016] As a further solution of the present invention: the process of interpolation replacement is:

[0017] Obtain the market price of the abnormal value in the past m collection cycles, and calibrate the abnormal value according to the weighted moving average method. The formula is:

[0018] ;

[0019] Among them, P x represents the value after outlier interpolation, P j represents the jth market price in m acquisition cycles, w j represents the weight value of the jth market price, and the weight value increases with time sequence, w j =j / (m+1).

[0020] As a further solution of the present invention: in the information collection module, every time the purchase price is re-determined with the supplier, the collection cycle is adjusted to T 原.

[0021] As a further solution of the present invention: in the price comparison prompt module, when the market price of an item collected in any collection period is lower than A% of the purchase price of the item, the total duration of all collection periods after the purchase price is determined is marked. If the total duration is lower than the preset duration, the supplier this time is determined as a risky supplier.

[0022] As a further solution of the present invention: the cycle adjustment module is also used to set an upper limit for the length of the collection cycle. When the length of the collection cycle reaches the upper limit, even if the adjustment coefficient α is greater than 1, the lengths of the next n collection cycles still remain at the upper limit.

[0023] As a further solution of the present invention: the price comparison prompt module also includes an automatic bargaining unit. When it is detected that the market price of the item is lower than a set threshold, the system automatically initiates a bargaining request to the supplier.

[0024] Beneficial effects of the present invention:

[0025] The present invention automatically collects the market price sequence of items at regular intervals by setting the duration of the initial collection cycle. The system mines out relevant price indicators based on these market price sequences. By analyzing these price indicators, the system can understand the changing trend of the current market price. According to the changing trend of the price indicators in the current collection cycle, the system automatically adjusts the duration of the collection cycle. When the market price of the item decreases, the system shortens the collection cycle so as to collect price data more frequently, thereby more accurately grasping the market dynamics. On the contrary, if the market price is stable or rising, the system will extend the collection cycle to reduce unnecessary data collection and processing work. This adaptive mechanism enables the present invention to effectively cope with market price fluctuations, respond in time, and follow up market dynamics. When the market price drops rapidly, the system can quickly capture this change and take corresponding measures, such as renegotiating the procurement contract, finding a more competitive supplier, etc. This helps enterprises reduce procurement costs and improve economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The present invention will be further described below in conjunction with the accompanying drawings.

[0027] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] See also Figure 1 As shown, the present invention is an adaptive price inquiry and comparison service optimization management system based on artificial intelligence, which aims to improve the response speed and accuracy of enterprises to market price changes in the procurement process through intelligent means. The system is mainly composed of four core modules: information collection module, information processing module, cycle adjustment module and price comparison prompt module. The functions of these four modules are described in detail below:

[0030] Information collection module

[0031] Functional description: This module is responsible for regularly collecting market price information of specific items. Users can set the initial information collection period (for example, daily or weekly).

[0032] Operation process:

[0033] At set intervals (i.e., collection cycles), the system automatically obtains the latest market prices of target products from designated channels, which may include e-commerce platforms, supplier websites, industry databases, etc.

[0034] After every n collection cycles, the system will generate a sequence of all recorded prices during that period and extract the most recent market price P. This step ensures the timeliness and accuracy of the data.

[0035] At the same time, calculate how many data points in this price series are lower than the preset item purchase cost P0, and record this ratio as B. This ratio reflects the changing trend of market supply and demand.

[0036] Based on these data, a line graph is drawn to reflect the trend of market prices over time, and an attempt is made to approximate this curve using a piecewise function f(t), where t represents the length of time that has passed since the first collection point, and the range is limited to [1, n]. This mathematical model helps capture complex price fluctuation patterns.

[0037] Finally, the two ends of the line graph are directly connected to form a straight line F(t) to simplify the analysis process. Although this method sacrifices some details, it can quickly give the overall trend.

[0038] Information processing module

[0039] Function description: Use the collected data to evaluate whether it is necessary to adjust the subsequent price monitoring frequency.

[0040] Implementation:

[0041] By comprehensively considering the most recently observed price P, the proportion B below the average purchase price, the area (integral value) under the piecewise function f(t) and the area under the linear function F(t), a coefficient called α is calculated as the basis for adjusting the length of the next n data collection cycles. Specifically, the value of α depends on multiple factors, including but not limited to the degree of difference between the current market price and the historical average level, the magnitude of price fluctuations, and the stability of long-term trends.

[0042] The specific calculation formula of α is:

[0043] ;

[0044] Here, β is an adjustable parameter used to fine-tune the final result; f'(t) represents the derivative of the piecewise function at a certain point; and F''(x) refers to the result of the second derivative of the linear function about the x-axis. This design allows the system to flexibly adjust its behavior according to different application scenarios.

[0045] Cycle Adjustment Module

[0046] Function description: Dynamically modify the data collection frequency in the next period of time based on the adjustment coefficient α obtained from the previous stage analysis.

[0047] Execution steps:

[0048] After completing n rounds of data collection, the total time required for the next round of n sampling is reset according to the currently calculated α value. 新 =T 原 ×α. If α>1, it means that the interval between each check should be increased; vice versa. This approach allows the system to automatically adapt to changes in the external environment according to actual conditions, thereby maintaining efficient operation while reducing unnecessary resource consumption.

[0049] In addition, other external variables such as holiday effects and seasonal demand can be considered to further optimize model performance. For example, monitoring efforts can be increased in advance to capture potential opportunities during periods when a large number of promotional activities are expected to occur.

[0050] Price comparison module

[0051] Function description: Warn users when it is found that the actual selling price of an item is much lower than its standard purchase price.

[0052] Trigger condition: If the observed selling price of a product is at least A% lower than the pre-defined benchmark price in any given collection period (A is a user-defined percentage), the system will immediately notify relevant personnel to pay attention to possible price anomalies. This not only helps to discover potential cost-saving opportunities in a timely manner, but also helps companies avoid losses caused by ignoring important information.

[0053] In order to improve the user experience, more personalized setting options can be added, such as allowing users to choose how to receive notifications (email, SMS, in-app push, etc.), set sensitivity thresholds, etc. At the same time, more accurate suggestions and support services can be provided based on historical transaction records and personal preferences.

[0054] In a preferred embodiment of the present invention, the core task of the information collection module is to obtain the prices of items from multiple market data sources and determine the lowest value among these prices as the market price. This strategy helps ensure that enterprises can purchase the required goods at the most favorable price, thereby reducing costs.

[0055] Data sources: The data sources of market prices include but are not limited to online shopping malls, physical store prices, and historical transaction records. Online shopping malls provide real-time commodity prices, physical store prices reflect the supply and demand conditions of the offline market, and historical transaction records provide price trends and fluctuations over a period of time.

[0056] Lowest value selection: The system will automatically compare prices from different channels and select the lowest value as the current market price P. This step ensures that the company can obtain the most competitive quotation.

[0057] In another preferred embodiment of the present invention, the information collection module adds a data filtering unit for processing outliers in the market price sequence. These outliers may be caused by data entry errors, temporary market fluctuations or other abnormal factors. If they are not processed, they may affect subsequent data analysis and decision-making.

[0058] Outlier definition: An outlier is a value that differs too much from the average value of the market price series. Specifically, if the difference between a price point and the average value of the series exceeds a preset threshold, then this price point is considered an outlier.

[0059] Interpolation replacement: For detected outliers, the system will not simply delete them, but replace them by interpolation. This means that the system will calculate a reasonable estimate to replace the outlier based on the normal data points before and after the outlier. This method not only preserves the integrity of the data, but also avoids the impact of outliers on the overall trend analysis.

[0060] Advantages: By introducing a data filtering unit, the system can more accurately reflect the real trend of market price changes and reduce the interference caused by accidental factors. This is essential for formulating effective procurement strategies and predicting future price trends.

[0061] In a preferred case of this embodiment, the interpolation replacement process is:

[0062] Obtain the market price of the abnormal value in the past m collection cycles, and calibrate the abnormal value according to the weighted moving average method. The formula is:

[0063] ;

[0064] Among them, P x represents the value after outlier interpolation, P j represents the jth market price in m acquisition cycles, w j represents the weight value of the jth market price, and the weight value increases with time sequence, w j =j / (m+1), interpolate outliers through historical data.

[0065] In another preferred embodiment of the present invention, the information collection module is not only responsible for regularly collecting market price data, but also introduces an automatic adjustment mechanism after re-determining the purchase price with the supplier. This mechanism ensures that the frequency of data collection can be flexibly changed according to actual procurement activities, thereby improving the response speed and accuracy of the system.

[0066] Redefine the purchase price: When an enterprise reaches a new purchase agreement or contract with a supplier and determines a new purchase price, the system will automatically adjust the current collection cycle to the initially set cycle length Toriginal.

[0067] Purpose: This adjustment helps to reassess the market situation under the new price system and ensure the timeliness and relevance of the data. At the same time, it also provides companies with a period of time to observe the market reaction under the new price system and provide a basis for subsequent decision-making.

[0068] Advantages: In this way, companies can better adapt to market changes, adjust procurement strategies in a timely manner, and reduce risks caused by market price fluctuations.

[0069] In a preferred embodiment of the present invention, in the price comparison prompt module, the present invention introduces a risk assessment mechanism based on time series analysis. When the system detects that the market price of an item in a certain acquisition period is lower than A% of the current purchase price, a series of subsequent operations will be triggered to assess the reliability and risk level of the supplier.

[0070] The market price is lower than the purchase price by A%: This is the condition that triggers the risk assessment. A% is a user-defined threshold that identifies significant price differences.

[0071] Mark total duration: Once the conditions are met, the system will mark the total duration of all acquisition cycles since the last purchase price was determined. This total duration reflects the time span from the last purchase to the present when the market price has been continuously lower than the purchase price.

[0072] Risky supplier determination: If this total duration is lower than the preset threshold (e.g. 30 days), the system will determine the supplier as a risky supplier. This indicates that the supplier's price may not be stable enough or there are other potential supply issues.

[0073] Purpose: In this way, companies can promptly identify suppliers that may cause increased costs or unstable supply, so that they can take corresponding measures, such as renegotiating contracts, finding alternative suppliers, etc.

[0074] Advantages: This time series-based risk assessment method provides enterprises with a quantitative tool to monitor and manage supply chain risks, helping to maintain the long-term interests and market competitiveness of enterprises.

[0075] In another preferred embodiment of the present invention, in this embodiment, the cycle adjustment module is endowed with a new capability, namely, the ability to set a maximum limit on the length of the acquisition cycle, which is crucial for maintaining the stability and predictability of the data acquisition frequency.

[0076] Upper limit of the collection cycle: System administrators or users can preset a maximum collection cycle length based on actual business needs and resource conditions. This upper limit ensures that even when the theoretical cycle length calculated by the adjustment coefficient α exceeds the normal range, a reasonable monitoring frequency can be maintained to avoid affecting decision-making efficiency due to overly frequent or sparse data collection.

[0077] Processing logic when reaching the upper limit: When the next cycle length calculated based on the adjustment coefficient α exceeds the preset upper limit, the system will automatically limit the cycle length to the upper limit value, rather than strictly extending it according to the α value. This means that no matter how drastic the market fluctuations are, the interval of data collection will not be shortened indefinitely, ensuring the consistency and stability of data analysis.

[0078] Advantages: By introducing an upper limit on the collection cycle length, enterprises can effectively control the cost and complexity of data collection while ensuring the timeliness of data, ensuring the continuous and stable operation of the system.

[0079] In another preferred embodiment of the present invention, the price comparison prompt module integrates an advanced automatic bargaining unit, which further improves the initiative and efficiency of the enterprise in price negotiation.

[0080] Market price falls below threshold: The system continuously monitors the market price of an item and once it detects that the market price has fallen below a preset threshold, this usually means there is an opportunity for cost savings or a signal that the supplier may be willing to reduce the price further.

[0081] Automatically initiate bargaining requests: In this case, the system will not only send a price anomaly reminder to the user, but will also automatically generate and send bargaining requests to relevant suppliers. This process does not require manual intervention, greatly speeding up the response speed, and improving the timeliness and success rate of bargaining.

[0082] Automation of bargaining process: The automatic bargaining unit can configure a variety of bargaining strategies, such as based on historical transaction prices, market average prices or competitor quotations, to strive for a lower purchase price with the most favorable conditions. In addition, the system can also record the process and results of each bargaining, providing reference data for future bargaining activities.

[0083] Advantages: The addition of automatic bargaining function enables enterprises to participate in price negotiations more actively and seize every opportunity to save costs. At the same time, it also reduces the workload of procurement personnel, allowing them to focus on higher value tasks such as supplier relationship management and strategic procurement planning.

[0084] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. The adaptive price inquiry and comparison service optimization management system based on artificial intelligence is characterized by: include: The information collection module is used to set the initial duration of the collection cycle, collect the market price of any item every collection cycle, generate a market price sequence every n collection cycles, obtain the most recent market price P in the market price sequence, and the proportion B of the number of items in the market price sequence that are lower than the purchase price P0 of the item in the sequence, and draw a line coordinate graph of the market price changing over time, and represent the line with a piecewise function f(t), t∈[1,n], connect the first and last coordinate points of the line graph, and represent the obtained connection line with a straight line function F(t); The information processing module is used to calculate the adjustment coefficient α of the collection period according to the market price index, wherein the market price index includes the latest market price P, the ratio B, the integral of the piecewise function f(t) and the integral of the linear function F(x), and the adjustment coefficient α of the collection period is calculated by the following formula: ； Where β represents the correction coefficient; The cycle adjustment module is used to calculate the adjustment coefficient α according to the market price index every n collection cycles, and mark the duration of the current collection cycle as T 原 , then adjust the duration T of the next n acquisition cycles according to the adjustment coefficient α 新 =T 原 α; The price comparison prompt module is used to issue a purchase price abnormality prompt when the market price of the item collected in any collection period is lower than A% of the current purchase price of the item, where A is a set value; The cycle adjustment module is also used to set an upper limit for the duration of the collection cycle. When the duration of the collection cycle reaches the upper limit, even if the adjustment coefficient α is greater than 1, the durations of the next n collection cycles still remain at the upper limit.

2. The artificial intelligence-based adaptive price inquiry and comparison service optimization management system according to claim 1 is characterized in that: In the information collection module, the market price is the lowest value among the prices of items from all market data sources, and the data sources include online shopping malls, physical store prices and transaction records.

3. The artificial intelligence-based adaptive price inquiry and comparison service optimization management system according to claim 1 is characterized in that: The information collection module also includes a data filtering unit, which is used to interpolate and replace abnormal values ​​in the market price sequence, where the abnormal values ​​are values ​​that differ too much from the average value of the market price sequence.

4. The artificial intelligence-based adaptive price inquiry and comparison service optimization management system according to claim 3 is characterized in that: The interpolation replacement process is: Obtain the market price of the abnormal value in the past m collection cycles, and calibrate the abnormal value according to the weighted moving average method. The formula is: ； Among them, P x represents the value after outlier interpolation, P j represents the jth market price in m acquisition cycles, w j represents the weight value of the jth market price, and the weight value increases with time sequence, w j =j / (m+1).

5. The artificial intelligence-based adaptive price inquiry and comparison service optimization management system according to claim 1 is characterized in that: In the information collection module, each time the purchase price is re-determined with the supplier, the collection cycle is adjusted to T 原 .

6. The artificial intelligence-based adaptive price inquiry and comparison service optimization management system according to claim 5 is characterized in that: In the price comparison prompt module, when the market price of an item collected in any collection period is lower than A% of the purchase price of the item, the total duration of all collection periods after the purchase price is determined is marked. If the total duration is lower than the preset duration, the supplier this time is determined as a risky supplier.

7. The artificial intelligence-based adaptive price inquiry and comparison service optimization management system according to claim 1 is characterized in that: The price comparison prompt module also includes an automatic bargaining unit. When it is detected that the market price of an item is lower than a set threshold, the system automatically initiates a bargaining request to the supplier.

Images