Price index calculation method and system supporting multi-dimensional information statistics

Abstract

The invention relates to the technical field of information statistics, and discloses a price index calculation system supporting multi-dimensional information statistics, which comprises a data acquisition module, a data dimension setting module, an abnormal data rejection range setting module, a price index calculation module, a price index display module and an external interface module, the data acquisition module is used for acquiring a unit for calculating a price index; the invention also provides a price index calculation method supporting multi-dimensional information statistics, and the method comprises the following steps: S1, calculating the weight of a price unit, and collecting the data of the price index through a data collection module; according to the method, richer information can be provided for prediction of the price change trend, deeper understanding of the dynamic change of the price is facilitated, and automatic elimination of abnormal data and dynamic adjustment of the weight of the price unit can be realized, so that the accuracy of price index calculation is ensured, and the change trend of the price is reflected more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of information statistics, and in particular to a price index calculation method and system supporting multi-dimensional information statistics. Background Art

[0002] A price index is an economic indicator used to measure changes in the price level of a group of goods or services. It expresses the trend and degree of price changes in the form of relative numbers by comparing the price levels of the reporting period and the base period. Price indices can be used to reflect the direction, trend and degree of changes in commodity prices over different periods. There are various types of price indices around the world, such as the Consumer Price Index (CPI) and the Producer Price Index (PPI), which measure the price changes of a basket of goods and services. These indices are of great significance to government policy making, academic research and investor decision-making.

[0003] However, the above price index often only calculates the price index for one or two information dimensions of a certain type of commodity. The single-dimensional index calculation cannot fully display the overall picture and internal structure of the data, and may miss some important information. Therefore, multi-dimensional statistics are needed to more comprehensively understand the characteristics and laws of the data. Through multi-dimensional data analysis and comparison, the correlation and trend between the data can be discovered, providing more accurate and comprehensive support for decision-making.

[0004] Before calculating the price index, it is necessary to collect sample data and use manual identification and manual removal to remove abnormal data in the collected data. There will be some misjudgments and missed judgments when using manual identification and manual removal. At the same time, manual removal of anomalies may be affected by the subjective factors of analysts, and different people may have different judgments on the same set of data. When the amount of data is large, manual removal of outliers will be very time-consuming and inefficient. Therefore, it is necessary to use statistical methods to automatically screen and clean the data to ensure the objectivity of abnormal data identification and improve the efficiency of abnormal data removal. At the same time, the algorithm for automatically removing abnormal data can be reused for multiple data sets to obtain consistent processing results.

[0005] Common price index models, such as the Consumer Price Index (CPI), often fix the weight value of each price unit in the same calculation cycle, and only adjust the weight of the price unit between each calculation cycle. This weight setting method cannot adjust the weight in real time to adapt to different scenarios, has strong manual intervention, and subjective factors have a greater impact on the price index calculation results. Therefore, a method for dynamically adjusting the weight of the price unit is needed, which can automatically adjust the weight according to the user settings to cope with different price index calculation situations and needs, reduce manual intervention, and reduce the impact of subjective factors on the index calculation results. Summary of the invention

[0006] 1. Technical issues to be resolved

[0007] In view of the shortcomings of the prior art, the present invention provides a price index calculation method and system that supports multi-dimensional information statistics, mainly to solve the existing common price index models, such as the Consumer Price Index (CPI), etc., in which the weight value of each price unit is often fixed in the same calculation cycle, and the weight of the price unit is only adjusted between each calculation cycle. This weight setting method cannot adjust the weight in real time to adapt to different scenarios, has strong manual intervention, and subjective factors have a greater impact on the price index calculation results.

[0008] (II) Technical solution

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] A price index calculation system supporting multi-dimensional information statistics comprises a data acquisition module, a data dimension setting module, an abnormal data elimination range setting module, a price index calculation module, a price index display module and an external interface module, wherein the data acquisition module is used to collect units for calculating the price index, the data dimension setting module is connected to the data acquisition module, and is used to allow a price index calculator to select a dimension required for calculating the price index from multiple dimensions, the abnormal data elimination range setting module is connected to the data dimension device module, and is used to allow a price index calculator to set upper and lower limits of a price index contribution, the price index calculation module is connected to the data acquisition module, the data dimension setting module, and the abnormal data elimination range setting module, and is used to receive data collected by the data acquisition module, data dimensions set by the data dimension setting module, and upper and lower limits of a contribution set by the abnormal data elimination module, and performs multi-dimensional calculations on the price index according to the received data, the price index display module is connected to the price index calculation module, and is used to receive an output result of the price index calculation module, and the external interface module is connected to the price index display module, and is used to receive an external data call request and provide the price index calculation result to the outside.

[0011] Furthermore, the data collection module records the collected price index units as X1 (D1, D2, ... D M ,P X1R ,Q X1R ,P X1R-1 ,Q X1R-1 ), X2(D1, D2, ...D M ,P X2R ,Q X2R ,P X2R-1 ,Q X2R-1 )...XN (D1, D2, ...D M ,P XNR ,Q XNR ,P XNR-1 ,Q XNR-1 ), where X1, X2, ...X N is the price unit, D1, D2, ...D M is the dimension of the price unit, where P X1R , P X2R ,...P XNR is the unit price of each price unit during the reporting period, Q X1R , Q X2R ,...Q XNR is the purchase volume of each price unit during the reporting period, P X1R-1 , P X2R -1,...P XNR-1 is the base period unit price of each price unit, Q X1R-1 , Q X2R -1,...Q XNR-1 is the base period purchase quantity for each price unit.

[0012] On the basis of the above scheme, the dimensions of the price unit are any number of dimensions including the origin, factory price, validity period, classification, material, color, and shape of the commodity.

[0013] As a further solution of the present invention, the data dimension setting module allows the price index calculator to select D1, D2, ...D M The dimension required to calculate the price index is selected from many dimensions. Through dimension selection, the original data collection mark is changed from X1 (D1, D2, ... D M ,P X1R ,Q X1R ,P X1R-1 ,Q X1R-1 ), X2(D1, D2, ...D M ,P X2R ,Q X2R ,P X2R-1 ,Q X2R-1 )...X N (D1, D2, ...D M ,P XNR ,Q XNR ,P XNR-1 ,Q XNR-1 ) and so on to X1(D C1 , D C2 ,...D CM ,P X1R ,Q X1R ,P X1R-1 ,Q X1R-1 ), X2(DC1 , D C2 ,...D CM ,P X2R ,Q X2R ,P X2R-1 ,Q X2R-1 )...X N (D C1 , D C2 ,...D CM ,P XNR ,Q XNR ,P XNR-1 ,Q XNR-1 ), the original collected data dimensions are D1, D2, ...D M Change to D C1 , D C2 ,...D CM .

[0014] Furthermore, after each round of calculation results are generated, the price index calculation module removes abnormal data according to the upper and lower limits of contribution set by the calculator, and recalculates the weight of each price unit until the contribution of each price unit falls within the range of normal data.

[0015] On the basis of the above scheme, the price index display module will receive the output results of the price index calculation module in the form of various statistical charts such as histograms, curve graphs, scatter plots, line graphs, pie charts, etc. to display the quarterly changes, annual changes of the calculated commodity price index and the contribution of each commodity in the reporting period.

[0016] The present invention also proposes a price index calculation method supporting multi-dimensional information statistics, comprising the following steps:

[0017] S1: Calculate the price unit weight, collect the price index data through the data collection module, and collect the price unit data X1, X2, ...X N In the example, the i-th price unit is: X i (D C1 , D C2 ,...D CM ,P XiR ,Q XiR ,P XiR-1 ,Q XiR-1 ), where: Q XiR-1 The base period purchase volume of this price unit, then the weight of the i-th price unit is:

[0018]

[0019] S2: Calculate the price index of a single calculation dimension and a combined calculation dimension. The data dimension set by the user in the data dimension setting module is D C1 , D C2 ,...D CM , then D C1 , D C2 ,...D CM The combination of any two or more dimensions is the combined calculation dimension, denoted as M. Due to the reduction of calculation dimensions, X1, X2, ...X N There will be price units with the same content. For price units with the same content, the reporting period price P of each price unit must be recalculated in the following way. XMR 、Purchase quantity Q during the reporting period XMR , base period price P XMR-1 and base period purchase quantity Q XMR-1 , and then calculate the price index of each combination dimension;

[0020] S3: Calculate the contribution of each price unit to the price index of each dimension, and convert the price unit X I and price index Z M By the following formula: Perform calculations;

[0021] S4: Range judgment, judging the contribution of the price index of each dimension calculated in S3, and judging whether the contribution is within an appropriate range. If it is within the appropriate range, the calculation ends directly; if it is not within the appropriate range, perform the following steps.

[0022] S4: Eliminate abnormal price unit data according to the upper and lower limits of abnormal data set by the abnormal data elimination range setting module: C UP , C DOWN , combined with the contribution G calculated in the previous step I , the contribution G I Not in C UP , C DOWN The price unit data in the range is removed, and only C is retained DOWN ≤G I ≤C UP Price unit;

[0023] S5: Dynamically adjust the price unit weights, according to the price units in S4, the original price units X1, X2, ...X N Change to X T1 , X T2 ,...X TN , for X T1 , X T2 ,...XTN Repeat the calculations from S1 to S4 until the contribution of each price unit falls within C UP and C DOWN within the scope;

[0024] S6: After the calculation is completed, the price index calculation results and calculation process data are stored in the cloud for preservation. When a price index data call request is received, the price data is provided to the outside.

[0025] Furthermore, when calculating the price index of the combination dimension in S2, it is assumed that X in the price unit P , X P+1 ...X q For price units with the same content, then:

[0026]

[0027] From the above, we can see that the price index of the M dimension is:

[0028] (III) Beneficial effects

[0029] Compared with the prior art, the present invention provides a price index calculation method and system supporting multi-dimensional information statistics, which has the following beneficial effects:

[0030] 1. Any enterprise or individual in the present invention can perform multi-dimensional index calculation and data analysis when calculating any price index. In addition to the calculation of the basic price index, multi-dimensional calculation can be performed through multi-dimensional selection of product types, inclusion and exclusion of factors such as regions and time, etc., to provide richer information for the prediction of price change trends, which helps to have a deeper understanding of the dynamic changes of prices.

[0031] 2. The present invention also supports automatic elimination of abnormal data and dynamic adjustment of price unit weights to ensure the accuracy of price index calculation and more accurately reflect price trends.

[0032] 3. The present invention solves the problem of single dimension when calculating price index by setting price unit dimensions, selecting multiple dimensions and calculating price index of multiple dimensions. It also solves the problem of manual removal of abnormal data when calculating price index by setting abnormal data removal range. It also solves the problem of fixed weight when calculating price index by dynamically adjusting weight of each price unit through dynamic weight adjustment algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a schematic diagram of the framework structure of a price index calculation system supporting multi-dimensional information statistics proposed by the present invention;

[0034] Figure 2 A schematic diagram of the process structure of a price index calculation method supporting multi-dimensional information statistics proposed by the present invention. DETAILED DESCRIPTION

[0035] 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.

[0036] Example 1

[0037] Reference Figure 1-Figure 2 A price index calculation system supporting multi-dimensional information statistics includes a data collection module, a data dimension setting module, an abnormal data elimination range setting module, a price index calculation module, a price index display module and an external interface module. The data collection module is used to collect units for calculating the price index. The data dimension setting module is connected to the data collection module and is used to allow the price index calculator to select the dimension required for calculating the price index from multiple dimensions. The abnormal data elimination range setting module is connected to the data dimension device module and is used to allow the price index calculator to set the upper and lower limits of the price index contribution, support automatic elimination of abnormal data, and dynamic adjustment of price unit weights to ensure In order to ensure the accuracy of price index calculation and reflect the price trend more accurately, the price index calculation module is connected with the data acquisition module, the data dimension setting module and the abnormal data elimination range setting module, and is used to receive the data collected by the data acquisition module, the data dimension set by the data dimension setting module and the upper and lower limits of contribution set by the abnormal data elimination module, and perform multiple calculations on the price index based on the received data. The price index display module is connected with the price index calculation module and is used to receive the output results of the price index calculation module. The external interface module is connected with the price index display module and is used to receive external data call requests and provide price index calculation results to the outside.

[0038] In the present invention, the data collection module records the collected price index unit as X1 (D1, D2, ... D M ,P X1R ,Q X1R ,P X1R-1 ,Q X1R-1 ), X2(D1, D2, ...D M ,P X2R ,Q X2R ,P X2R-1 ,Q X2R-1 )...X N (D1, D2, ...DM ,P XNR ,Q XNR ,P XNR-1 ,Q XNR-1 ), where X1, X2, ...X N is the price unit, D1, D2, ...D M is the dimension of the price unit, where P X1R , P X2R ,...P XNR is the unit price of each price unit during the reporting period, Q X1R , Q X2R ,...Q XNR is the purchase volume of each price unit during the reporting period, P X1R-1 , P X2R -1,...P XNR-1 is the base period unit price of each price unit, Q X1R-1 , Q X2R-1 ,...Q XNR-1 The base period purchase volume of each price unit. The dimensions of the price unit are the origin, ex-factory price, validity period, classification, and material of the product. Through multi-dimensional selection of product types, inclusion and exclusion of factors such as region and time, multi-dimensional calculation is performed to provide richer information for the prediction of price change trends, which helps to have a deeper understanding of the dynamic changes of prices. The data dimension setting module allows price index calculators to select D1, D2, ...D M The dimension required to calculate the price index is selected from many dimensions. Through dimension selection, the original data collection mark is changed from X1 (D1, D2, ... D M ,P X1R ,Q X1R ,P X1R-1 ,Q X1R-1 ), X2(D1, D2, ...D M ,P X2R ,Q X2R ,P X2R-1 ,Q X2R-1 )...X N (D1, D2, ...D M ,P XNR ,Q XNR ,P XNR-1 ,Q XNR-1 ) and so on to X1(D C1 , D C2 ,...D CM ,P X1R ,Q X1R ,P X1R-1 ,Q X1R-1 ), X2(D C1 , D C2 ,...D CM ,PX2R ,Q X2R ,P X2R-1 ,Q X2R-1 )...X N (D C1 , D C2 ,...D CM ,P XNR ,Q XNR ,P XNR-1 ,Q XNR-1 ), the original collected data dimensions are D1, D2, ...D M Change to D C1 , D C2 ,...D CM After each round of calculation results are generated, the price index calculation module eliminates abnormal data according to the upper and lower limits of contribution set by the calculator, and recalculates the weight of each price unit until the contribution of each price unit falls within the range of normal data. The price index display module receives the output results of the price index calculation module in the form of various statistical charts such as histograms, curve graphs, scatter plots, line graphs, pie charts, etc. to display the quarterly changes, annual changes of the calculated commodity price index and the contribution of each commodity in the reporting period.

[0039] The present invention also proposes a price index calculation method supporting multi-dimensional information statistics, comprising the following steps:

[0040] S1: Calculate the price unit weight, collect the price index data through the data collection module, and collect the price unit data X1, X2, ...X N In the example, the i-th price unit is: X i (D C1 , D C2 ,...D CM ,P XiR ,Q XiR ,P XiR-1 ,Q XiR-1 ), where: Q XiR-1 The base period purchase volume of this price unit, then the weight of the i-th price unit is:

[0041]

[0042] S2: Calculate the price index of a single calculation dimension and a combined calculation dimension. The data dimension set by the user in the data dimension setting module is D C1 , D C2 ,...D CM , then D C1 , D C2 ,...D CMThe combination of any two or more dimensions is the combined calculation dimension, denoted as M. Due to the reduction of calculation dimensions, X1, X2, ...X N There will be price units with the same content. For price units with the same content, the reporting period price P of each price unit must be recalculated in the following way. XMR 、Purchase quantity Q during the reporting period XMR , base period price P XMR-1 and base period purchase quantity Q XMR-1 , and then calculate the price index of each combination dimension;

[0043] S3: Calculate the contribution of each price unit to the price index of each dimension, and convert the price unit X I and price index Z M By the following formula: Perform calculations;

[0044] S4: Range judgment, judging the contribution of the price index of each dimension calculated in S3, and judging whether the contribution is within an appropriate range. If it is within the appropriate range, the calculation ends directly; if it is not within the appropriate range, perform the following steps.

[0045] S4: Eliminate abnormal price unit data according to the upper and lower limits of abnormal data set by the abnormal data elimination range setting module: C UP , C DOWN , combined with the contribution G calculated in the previous step I , the contribution G I Not in C UP , C DOWN The price unit data in the range is removed, and only C is retained DOWN ≤G I ≤C UP If the user sets the exclusion range to C UP and C DOWN , then when calculating the price index, first use C UP and C DOWN Perform one or more multi-dimensional price index calculations for the box. Except for the first calculation, each calculation removes the price units outside the box to ensure that the calculation results can accurately reflect the price changes;

[0046] S5: Dynamically adjust the price unit weights, according to the price units in S4, the original price units X1, X2, ...X N Change to X T1 , X T2 ,...X TN , for X T1 , X T2,...X TN Repeat the calculations from S1 to S4 until the contribution of each price unit falls within C UP and C DOWN within the scope;

[0047] S6: After the calculation is completed, the price index calculation results and calculation process data are stored in the cloud for preservation. When a price index data call request is received, the price data is provided to the outside.

[0048] In particular, when calculating the price index of the combination dimension in S2, it is assumed that X P , X P+ 1...X q For price units with the same content, then:

[0049]

[0050] From the above, we can see that the price index of the M dimension is:

[0051] Example 2

[0052] Reference Figure 1-Figure 2 A price index calculation system supporting multi-dimensional information statistics includes a data collection module, a data dimension setting module, an abnormal data elimination range setting module, a price index calculation module, a price index display module and an external interface module. The data collection module is used to collect units for calculating the price index. The data dimension setting module is connected to the data collection module and is used to allow the price index calculator to select the dimension required for calculating the price index from multiple dimensions. The abnormal data elimination range setting module is connected to the data dimension device module and is used to allow the price index calculator to set the upper and lower limits of the price index contribution, support automatic elimination of abnormal data, and dynamic adjustment of price unit weights. To ensure the accuracy of price index calculation and reflect the price trend more accurately, the price index calculation module is connected to the data acquisition module, the data dimension setting module, and the abnormal data elimination range setting module. It is used to receive the data collected by the data acquisition module, the data dimension set by the data dimension setting module, and the upper and lower limits of contribution set by the abnormal data elimination module, and perform multiple calculations on the price index based on the received data. The price index display module is connected to the price index calculation module to receive the output results of the price index calculation module. The external interface module is connected to the price index display module to receive external data call requests and provide price index calculation results to the outside.

[0053] In the present invention, the data collection module records the collected price index unit as X1 (D1, D2, ... D M ,P X1R ,Q X1R ,PX1R-1 ,Q X1R-1 ), X2(D1, D2, ...D M ,P X2R ,Q X2R ,P X2R-1 ,Q X2R-1 )...X N (D1, D2, ...D M ,P XNR ,Q XNR ,P XNR-1 ,Q XNR-1 ), where X1, X2, ...X N is the price unit, D1, D2, ...D M is the dimension of the price unit, where P X1R , P X2R ,...P XNR is the unit price of each price unit during the reporting period, Q X1R , Q X2R ,...Q XNR is the purchase volume of each price unit during the reporting period, P X1R-1 , P X2R-1 ,...P XNR-1 is the base period unit price of each price unit, Q X1R-1 , Q X2R-1 ,...Q XNR-1 The base period purchase volume of each price unit. The dimensions of the price unit are the origin, classification, material, color, and shape of the product. Through multi-dimensional selection of product types, inclusion and exclusion of factors such as region and time, multi-dimensional calculations are performed to provide richer information for the prediction of price change trends, which helps to gain a deeper understanding of the dynamic changes in prices. The data dimension setting module allows price index calculators to select D1, D2, ...D M The dimension required to calculate the price index is selected from many dimensions. Through dimension selection, the original data collection mark is changed from X1 (D1, D2, ... D M ,P X1R ,Q X1R ,P X1R-1 ,Q X1R-1 ), X2(D1, D2, ...D M ,P X2R ,Q X2R ,P X2R-1 ,Q X2R-1 )...X N (D1, D2, ...D M ,P XNR ,Q XNR ,P XNR-1 ,Q XNR-1 ) and so on to X1(D C1 , DC2 ,...D CM ,P X1R ,Q X1R ,P X1R-1 ,Q X1R-1 ), X2(D C1 , D C2 ,...D CM ,P X2R ,Q X2R ,P X2R-1 ,Q X2R-1 )...X N (D C1 , D C2 ,...D CM ,P XNR ,Q XNR ,P XNR-1 ,Q XNR-1 ), the original collected data dimensions are D1, D2, ...D M Change to D C1 , D C2 ,...D CM After each round of calculation results are generated, the price index calculation module eliminates abnormal data according to the upper and lower limits of contribution set by the calculator, and recalculates the weight of each price unit until the contribution of each price unit falls within the range of normal data. The price index display module receives the output results of the price index calculation module in the form of various statistical charts such as histograms, curve graphs, scatter plots, line graphs, pie charts, etc. to display the quarterly changes, annual changes of the calculated commodity price index and the contribution of each commodity in the reporting period.

[0054] The present invention also proposes a price index calculation method supporting multi-dimensional information statistics, comprising the following steps:

[0055] S1: Calculate the price unit weight, collect the price index data through the data collection module, and collect the price unit data X1, X2, ...X N In the example, the i-th price unit is: X i (D C1 , D C2 ,...D CM ,P XiR ,Q XiR ,P XiR-1 ,Q XiR-1 ), where: Q XiR-1 The base period purchase volume of this price unit, then the weight of the i-th price unit is:

[0056]

[0057] S2: Calculate the price index of a single calculation dimension and a combined calculation dimension. The data dimension set by the user in the data dimension setting module is D C1 , D C2 ,...D CM , then D C1 , D C2 ,...D CM The combination of any two or more dimensions is the combined calculation dimension, denoted as M. Due to the reduction of calculation dimensions, X1, X2, ...X N There will be price units with the same content. For price units with the same content, the reporting period price P of each price unit must be recalculated in the following way. XMR 、Purchase quantity Q during the reporting period XMR , base period price P XMR-1 and base period purchase quantity Q XMR-1 , and then calculate the price index of each combination dimension;

[0058] S3: Calculate the contribution of each price unit to the price index of each dimension, and convert the price unit X I and price index Z M By the following formula: Perform calculations;

[0059] S4: Range judgment, judging the contribution of the price index of each dimension calculated in S3, and judging whether the contribution is within an appropriate range. If it is within the appropriate range, the calculation ends directly; if it is not within the appropriate range, perform the following steps.

[0060] S4: Eliminate abnormal price unit data according to the upper and lower limits of abnormal data set by the abnormal data elimination range setting module: C UP , C DOWN , combined with the contribution G calculated in the previous step I , the contribution G I Not in C UP , C DOWN The price unit data in the range is removed, and only C is retained DOWN ≤G I ≤C UP If the user sets the exclusion range to C UP and C DOWN , then when calculating the price index, first use C UP and C DOWN Perform one or more multi-dimensional price index calculations for the box. Except for the first calculation, each calculation removes the price units outside the box to ensure that the calculation results can accurately reflect the price changes;

[0061] S5: Dynamically adjust the price unit weights, according to the price units in S4, the original price units X1, X2, ...X N Change to X T1 , X T2 ,...X TN , for X T1 , X T2 ,...X TN Repeat the calculations from S1 to S4 until the contribution of each price unit falls within C UP and C DOWN within the scope;

[0062] S6: After the calculation is completed, the price index calculation results and calculation process data are stored in the cloud for preservation. When a price index data call request is received, the price data is provided to the outside.

[0063] In particular, when calculating the price index of the combination dimension in S2, it is assumed that X P , X P+ 1...X q For price units with the same content, then:

[0064]

[0065] From the above, we can see that the price index of the M dimension is:

[0066] In the description of this article, it should be noted that relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

Claims

1. A price index calculation system supporting multi-dimensional information statistics, comprising a data acquisition module, a data dimension setting module, an abnormal data elimination range setting module, a price index calculation module, a price index display module and an external interface module, characterized in that: The data acquisition module is used to collect units for calculating the price index. The data dimension setting module is connected to the data acquisition module to allow the price index calculator to select the dimension required for calculating the price index from multiple dimensions. The abnormal data elimination range setting module is connected to the data dimension device module to allow the price index calculator to set the upper and lower limits of the price index contribution. The price index calculation module is connected to the data acquisition module, the data dimension setting module, and the abnormal data elimination range setting module to receive the data collected by the data acquisition module, the data dimension set by the data dimension setting module, and the upper and lower limits of the contribution set by the abnormal data elimination module, and performs multiple calculations on the price index based on the received data. The price index display module is connected to the price index calculation module to receive the output result of the price index calculation module. The external interface module is connected to the price index display module to receive external data call requests and provide price index calculation results to the outside.

2. A price index calculation system supporting multi-dimensional information statistics according to claim 1, characterized in that: The data collection module records the collected price index units as X1 (D1, D2, ... D M ,P X1R ,Q X1R ,P X1R-1 ,Q X1R-1 ), X2(D1, D2, ...D M ,P X2R ,Q X2R ,P X2R-1 ,Q X2R-1 )...X N (D1, D2, ...D M ,P XNR ,Q XNR ,P XNR-1 ,Q XNR-1 ), where X1, X2, ...X N is the price unit, D1, D2, ...D M is the dimension of the price unit, where P X1R , P X2R ,...P XNR is the unit price of each price unit during the reporting period, Q X1R , Q X2R ,...Q XNR is the purchase volume of each price unit during the reporting period, P X1R-1 , P X2R-1 ,...P XNR-1 is the base period unit price of each price unit, Q X1R-1 , Q X2R-1 ,...Q XNR-1 is the base period purchase quantity for each price unit.

3. A price index calculation system supporting multi-dimensional information statistics according to claim 2, characterized in that: The dimensions of the price unit are any multiple dimensions of the origin, factory price, validity period, classification, material, color, and shape of the product.

4. A price index calculation system supporting multi-dimensional information statistics according to claim 1, characterized in that: The data dimension setting module allows the price index calculator to select D1, D2, ...D M The dimension required to calculate the price index is selected from many dimensions. Through dimension selection, the original data collection mark is changed from X1 (D1, D2, ... D M ,P X1R ,Q X1R ,P X1R-1 ,Q X1R-1 ), X2(D1, D2, ...D M ,P X2R ,Q X2R ,P X2R-1 ,Q X2R-1 )...X N (D1, D2, ...D M ,P XNR ,Q XNR ,P XNR-1 ,Q XNR-1 ) and so on to X1(D C1 , D C2 ,...D CM ,P X1R ,Q X1R ,P X1R-1 ,Q X1R-1 ), X2(D C1 , D C2 ,...D CM ,P X2R ,Q X2R ,P X2R-1 ,Q X2R-1 )...X N (D C1 , D C2 ,...D CM ,P XNR ,Q XNR ,P XNR-1 ,Q XNR-1 ), the original collected data dimensions are D1, D2, ...D M Change to D C1 , D C2 ,...D CM .

5. A price index calculation system supporting multi-dimensional information statistics according to claim 1, characterized in that: After each round of calculation results are generated, the price index calculation module removes abnormal data according to the upper and lower limits of contribution set by the calculator, and recalculates the weight of each price unit until the contribution of each price unit falls within the range of normal data.

6. A price index calculation system supporting multi-dimensional information statistics according to claim 1, characterized in that: The price index display module displays the output results of the received price index calculation module in the form of various statistical charts such as histograms, curve graphs, scatter plots, line graphs, pie charts, etc., showing the quarterly changes, annual changes of the calculated commodity price index, and the contribution of each commodity in the reporting period.

7. A price index calculation method supporting multi-dimensional information statistics, characterized in that: The following steps are involved: S1: Calculate the price unit weight, collect the price index data through the data collection module, and collect the price unit data X1, X2, ...X N In the example, the i-th price unit is: X i (D C1 , D C2 ,...D CM ,P XiR ,Q XiR ,P XiR-1 ,Q XiR-1 ), where: Q XiR-1 The base period purchase volume of this price unit, then the weight of the i-th price unit is: S2: Calculate the price index of a single calculation dimension and a combined calculation dimension. The data dimension set by the user in the data dimension setting module is D C1 , D C2 ,...D CM , then D C1 , D C2 ,...D CM The combination of any two or more dimensions is the combined calculation dimension, denoted as M. Due to the reduction of calculation dimensions, X1, X2, ...X N There will be price units with the same content. For price units with the same content, the reporting period price P of each price unit must be recalculated in the following way. XMR 、Purchase quantity Q during the reporting period XMR , base period price P XMR-1 and base period purchase quantity Q XMR-1 , and then calculate the price index of each combination dimension; S3: Calculate the contribution of each price unit to the price index of each dimension, and convert the price unit X I and price index Z M By the following formula: Perform calculations; S4: Range judgment, judging the contribution of the price index of each dimension calculated in S3, and judging whether the contribution is within an appropriate range. If it is within the appropriate range, the calculation ends directly; if it is not within the appropriate range, perform the following steps. S4: Eliminate abnormal price unit data according to the upper and lower limits of abnormal data set by the abnormal data elimination range setting module: C UP , C DOWN , combined with the contribution G calculated in the previous step I , the contribution G I Not in C UP , C DOWN The price unit data in the range is removed, and only C is retained DOWN ≤G I ≤C UP Price unit; S5: Dynamically adjust the price unit weights, according to the price units in S4, the original price units X1, X2, ...X N Change to X T1 , X T2 ,...X TN , for X T1 , X T2 ,...X TN Repeat the calculations from S1 to S4 until the contribution of each price unit falls within C UP and C DOWN within the scope; S6: After the calculation is completed, the price index calculation results and calculation process data are stored in the cloud for preservation. When a price index data call request is received, the price data is provided to the outside.

8. The price index calculation method supporting multi-dimensional information statistics according to claim 4, characterized in that: When calculating the price index of the combination dimension in S2, it is assumed that X P , X P+1 ...X q For price units with the same content, then: From the above, we can see that the price index of the M dimension is:

Images