Fast moving consumer goods market state evaluation method and system

Abstract

The invention discloses a fast moving consumer goods market state evaluation method and system, and belongs to the technical field of big data, fast moving consumer goods market state evaluation is realized based on a multi-dimensional weighted fitting model, and the method comprises the following steps: data acquisition: acquiring online and offline multi-channel data, deriving acquisition indexes through consumption and inventory records, and integrally constructing a complete index system; standardizing the indexes, constructing a standardization method based on the forward and reverse relationship between the collected indexes and the market state, and realizing the same-order relationship between the standardized indexes and the market state on the premise of eliminating the dimensional difference; index score conversion: based on the index standardization, realizing mapping from an index original value to a [0, 1] interval; combining weights of the indexes, measuring and calculating the indexes, and weighting the indexes; calculating a comprehensive score; and calculating a market state threshold value. According to the method, combination processing of indexes is realized, an end-to-end process from index acquisition to state evaluation is perfected and established, the market state is accurately evaluated, and the prediction capability is improved.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a method and system for evaluating the market status of fast-moving consumer goods. Background Art

[0002] In the field of fast-moving consumer goods, the depth and breadth of data collection are undergoing significant changes. In the past, data collection mainly relied on traditional sales channels and simple market research, with limited coverage and single data dimensions. Today, with the development of the Internet of Things, big data and artificial intelligence technologies, the breadth of data collection has been greatly expanded, covering multi-channel data such as online e-commerce platforms, social media, mobile applications, and smart shelves, RFID tags and POS systems in offline retail stores.

[0003] These data not only include consumer purchasing behavior, consumption habits and brand preferences, but also involve multiple dimensions such as market trends, competition analysis and supply chain management. At the same time, the depth of data collection is also constantly improving. The application of high-precision sensors and smart devices enables companies to monitor the inventory, sales and consumer interaction of goods in real time.

[0004] Market status analysis can help companies conduct predictive analysis, personalized recommendations, and supply chain optimization, thereby achieving more efficient operations and more accurate market insights. With these comprehensive and detailed data supports, fast-moving consumer goods companies can better grasp market dynamics, optimize products and services, enhance customer experience, and ultimately achieve sustainable development. With the continuous development of data analysis and machine learning technologies, how to develop indicator merging and processing through data analysis and machine learning technologies, build a scientific multi-indicator fusion solution, complete the quantification of market status, and find a reasonable method to qualitatively characterize market status are issues that need to be addressed. Summary of the invention

[0005] The technical task of the present invention is to address the above shortcomings and provide a method and system for evaluating the market status of fast-moving consumer goods, which can realize the combined processing of indicators, improve the end-to-end process from indicator collection to status evaluation, more accurately evaluate the market status, and improve the prediction ability.

[0006] The technical solution adopted by the present invention to solve its technical problem is:

[0007] A method for evaluating the market status of fast-moving consumer goods is provided, which realizes the evaluation of the market status of fast-moving consumer goods based on a multi-dimensional weighted fitting model. The implementation of the method includes:

[0008] 1) Data collection: collect data from multiple channels online and offline, and derive collection indicators from consumption and inventory records to build a complete indicator system;

[0009] 2) Indicator standardization: Based on the positive and negative relationship between the collected indicators and the market status, a standardization method is constructed to achieve the same magnitude relationship between the standardized indicators and the market status while eliminating the dimensional differences;

[0010] 3) Indicator score conversion, based on the indicator standardization, to achieve the mapping of the original indicator value to the [0,1] interval;

[0011] 4) Merge the weights of indicators, calculate indicators, and weight the indicators;

[0012] 5) Calculation of comprehensive score: based on the calculation result of the combined weight of the indicators, linear transformation is performed on the indicator scores to obtain a comprehensive score vector of the market status;

[0013] 6) Market status threshold measurement, using the estimated Gaussian mixture distribution results to determine the threshold, and referring to the number of market status intervals to determine the threshold division standard.

[0014] This method determines the collection plan by analyzing the nature of the collection indicators, analyzing the data distribution and data quality, determining the weighting plan, and analyzing the scores to determine the partitioning plan.

[0015] This method realizes the process of converting the indicator value into the indicator score, converting the indicator score into the total evaluation score, and converting the total evaluation score into the evaluation result.

[0016] Furthermore, the collected indicators include: market size, market growth rate, consumer loyalty, price sensitivity, inventory turnover rate, gross profit margin, consumer satisfaction and other indicators.

[0017] Furthermore, the index is standardized and the standardization method is constructed as follows:

[0018] Positive correlation: x ij =(x ij -min i x ij ) / (max i x ij -min i x ij );

[0019] Negative correlation: x ij =(max i x i -x ij ) / (max i x ij -min i x ij ).

[0020] Furthermore, when the indicator score conversion is evaluated in percentage in actual business, it is necessary to perform weighting based on the mapping, including:

[0021]

[0022] Furthermore, the indicators are combined with weights,

[0023] The indicator measurement methods include the use of principal component analysis (PCA) and factor analysis for indicator weights;

[0024] The eigenvector corresponding to the maximum eigenvalue is used for weighting. The larger the eigenvalue of the covariance matrix, the larger the variance of the corresponding eigenvector direction, and the more original feature information it represents. Therefore, the direction corresponding to the maximum eigenvalue is the direction with the largest variance. Each component of the eigenvector corresponds to the rotation component of the original variable, so the weighted new data is:

[0025]

[0026] where γ 1 Represents the eigenvector corresponding to the maximum eigenvalue, that is, the score of the first principal component on the original index.

[0027] Furthermore, the market status comprehensive score vector is recorded as:

[0028]

[0029] in Represents the weight result obtained based on statistical analysis of data.

[0030] Furthermore, the market status threshold calculation includes the following steps:

[0031] In the first step, the parameters of K Gaussian distributions are estimated by the EM algorithm. Assume that each Gaussian distribution is represented in ascending order of mean:

[0032] The second step is to determine the boundaries of each normal distribution according to the fluctuation size of each unit mean, and then calculate the fluctuation multiple:

[0033]

[0034] The third step is to determine the left threshold of the first Gaussian distribution and the right threshold of the kth Gaussian distribution, that is, the last Gaussian distribution, without using the fluctuation multiple; as well as the boundary of the intersection of two adjacent Gaussian distributions;

[0035] When K = 3, there are two results for determining the threshold, namely [μ 1 -σ1 , μ 1 +c 1 σ 1 , μ 2 +c 2 σ| 2 , μ 3 +σ 3 ]; [μ 1 -σ 1 , μ 1 +c 1 σ 1 , μ 3 -c 2 σ 3 , μ 3 +σ 3 ];

[0036] The fourth step is to judge the market status based on the threshold interval calculated in the third step; the method is interval mapping.

[0037] The present invention also claims protection for a fast-moving consumer goods market status evaluation system, comprising:

[0038] The data collection module is used to collect data from multiple channels online and offline, and to derive collection indicators from consumption and inventory records, thus building a complete indicator system as a whole;

[0039] The indicator standardization module builds a standardization method based on the positive and negative relationship between the collected indicators and the market status, and achieves the same magnitude relationship between the standardized indicators and the market status under the premise of eliminating the dimensional differences;

[0040] The indicator score conversion module, based on the indicator standardization module, realizes the mapping of the original indicator value to the [0,1] interval;

[0041] The indicator merging weight module is used to measure indicators and weight them;

[0042] The comprehensive score calculation module performs linear transformation on the indicator score based on the calculation result of the indicator merging weight module to obtain the comprehensive score vector of the market status;

[0043] The market status threshold calculation module uses the estimated Gaussian mixture distribution results to determine the threshold, and refers to the number of intervals of the market status to determine the threshold division standard;

[0044] The system specifically implements the evaluation of the market status of fast-moving consumer goods through the above-mentioned method.

[0045] Through various data collection methods, we collect indicator data that can reflect the market status;

[0046] Check and calibrate the indicator data to ensure that there are no missing or abnormal data;

[0047] Input the data into the indicator standardization module to complete the data standardization;

[0048] Input the standardized data into the indicator score conversion module to complete the score calculation of the data indicator;

[0049] Input the indicator scores into the indicator combined weight module to complete the calculation of indicator weights;

[0050] Input the index scores and index weights into the comprehensive score calculation module to complete the calculation of the comprehensive score;

[0051] Input the comprehensive score into the market status threshold calculation module to complete the market status threshold calculation;

[0052] The comprehensive score and the market status threshold are combined to obtain the market status corresponding to the comprehensive score.

[0053] The present invention also claims protection for a device for evaluating the market status of fast moving consumer goods, comprising: at least one memory and at least one processor;

[0054] The at least one memory is used to store a machine-readable program;

[0055] The at least one processor is used to call the machine-readable program to implement the above method.

[0056] The present invention also claims protection for a computer-readable medium having computer instructions stored thereon, which can implement the above method when executed by a processor.

[0057] Compared with the prior art, the method and system for evaluating the market status of fast-moving consumer goods of the present invention have the following advantages:

[0058] Beneficial effects:

[0059] The fast-moving consumer goods market status evaluation method of the present invention is based on a multi-dimensional weighted fitting model. By comprehensively considering factors of multiple dimensions (such as sales, market share, consumer satisfaction, etc.) and assigning different weights, it can more accurately evaluate the market status, improve forecasting capabilities, optimize decision support, improve operational efficiency, and enhance market insight, thereby helping companies to better formulate strategies and cope with risks in a highly competitive market. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a flowchart of a method for evaluating the market status of fast-moving consumer goods provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The present invention will be further described below in conjunction with specific embodiments.

[0062] The embodiment of the present invention provides a method for evaluating the market status of fast-moving consumer goods, which implements the market status evaluation of fast-moving consumer goods based on a multidimensional weighted fitting model, determines the collection plan by analyzing the properties of collection indicators, determines the weighting plan by analyzing data distribution and data quality, and determines the partition plan by analyzing the scores.

[0063] Combined with Figure 1 As shown, the implementation of this method is as follows:

[0064] 1. Data acquisition module:

[0065] In the field of fast-moving consumer goods, indicators such as market size, market growth rate, consumer loyalty, price sensitivity, inventory turnover rate, gross profit margin, and consumer satisfaction can well reflect the market situation. The above indicators are derived through data collection from multiple channels online and offline, as well as consumption and inventory records, to build a complete indicator system as a whole.

[0066] 2. Indicator standardization module:

[0067] Based on the positive and negative relationship between the collected indicators and the market status, a suitable standardization method is constructed, the purpose of which is to achieve the same magnitude relationship between the standardized indicators and the market status under the premise of eliminating the dimensional differences. The construction method is as follows:

[0068] Positive correlation: x ij =(x ij -min i x ij ) / (max i x ij -min i x ij );

[0069] Negative correlation: x ij =(max i x i -x ij ) / (max i x ij -min i x ij ).

[0070] 3. Index score conversion module:

[0071] Based on the standardization module, the mapping of the original value of the indicator to the interval [0,1] is realized. In actual business, it is often evaluated in percentage, so it is necessary to perform weighting on this basis, including:

[0072]

[0073] 4. Index merging weight module: perform index calculation and weight the index;

[0074] In this method, the indicator weights use principal component analysis (PCA) and factor analysis as optional indicator measurement methods.

[0075] Consider using the eigenvector corresponding to the maximum eigenvalue for weighting, because the larger the eigenvalue of the covariance matrix, the larger the variance of the corresponding eigenvector direction, and the more original feature information it represents, so the direction corresponding to the maximum eigenvalue is the direction with the largest variance. Each component of the eigenvector corresponds to the rotation component of the original variable, so the weighted new data is:

[0076]

[0077] where γ 1 Represents the eigenvector corresponding to the maximum eigenvalue, that is, the score of the first principal component on the original index.

[0078] 5. Comprehensive score calculation module:

[0079] In this method, the calculation results of the indicator weight module are linearly transformed with the indicator score to obtain the comprehensive score vector of the market status, which is recorded as:

[0080]

[0081] in Represents the weight result obtained based on statistical analysis of data.

[0082] 6. Market status threshold calculation module,

[0083] In this method, the results of the estimated Gaussian mixture distribution are used to define the threshold, and the number of intervals of the market state is referred to determine the threshold division standard.

[0084] In the first step, the parameters of K Gaussian distributions are estimated by the EM algorithm. Assume that each Gaussian distribution is represented in ascending order of mean:

[0085] The second step is to determine the boundaries of each normal distribution according to the fluctuation size of each unit mean, and then calculate the fluctuation multiple:

[0086]

[0087] The third step is to determine the left threshold of the first Gaussian distribution and the right threshold of the kth Gaussian distribution, that is, the last Gaussian distribution, without using the fluctuation multiple; as well as the boundary of the intersection of two adjacent Gaussian distributions;

[0088] When K = 3, there are two results for determining the threshold, namely [μ 1 -σ 1 , μ 1 +c 1 σ 1 , μ 2 +c 2 σ| 2 , μ 3 +σ 3 ]; [μ 1 -σ 1 , μ 1 +c 1 σ 1 , μ 3 -c 2 σ 3 , μ 3 +σ 3 ];

[0089] The fourth step is to judge the market status based on the threshold interval calculated in the third step; the method is interval mapping.

[0090] According to the above modules, this method can realize the evaluation of the market status of fast-moving consumer goods based on the multidimensional weighted fitting model:

[0091] Through various data collection methods, we collect indicator data that can reflect the market status;

[0092] Check and calibrate the indicator data to ensure that there are no missing or abnormal data;

[0093] Input the data into the indicator standardization module to complete the data standardization;

[0094] Input the standardized data into the indicator score conversion module to complete the score calculation of the data indicator;

[0095] Input the indicator scores into the indicator combined weight module to complete the calculation of indicator weights;

[0096] Input the index scores and index weights into the comprehensive score calculation module to complete the calculation of the comprehensive score;

[0097] Input the comprehensive score into the market status threshold calculation module to complete the market status threshold calculation;

[0098] The comprehensive score and the market status threshold are combined to obtain the market status corresponding to the comprehensive score.

[0099] This method realizes the process of converting indicator values ​​into indicator scores, indicator scores into evaluation scores, and evaluation scores into evaluation results. Based on algorithms such as principal components and Gaussian mixture models, the transformation from data indicators to comprehensive evaluation is realized, and a scientific market status assessment method is provided as a whole. The technical difficulty lies in the collection of business data, the construction of algorithms, and the adjustment of threshold parameters. It is necessary to adjust the process through continuous practice verification to improve the reliability and availability of the system.

[0100] The embodiment of the present invention further provides a system for evaluating the market status of fast-moving consumer goods. The system implements the evaluation of the market status of fast-moving consumer goods through the method for evaluating the market status of fast-moving consumer goods described in the above embodiment.

[0101] The system includes:

[0102] 1. Data collection module is used to collect data through multiple channels online and offline, as well as derive collection indicators from consumption and inventory records, including market size, market growth rate, consumer loyalty, price sensitivity, inventory turnover rate, gross profit margin, consumer satisfaction and other indicators, which can well reflect the market situation and build a complete indicator system as a whole.

[0103] 2. Indicator standardization module: Based on the positive and negative relationship between the collected indicators and the market status, a standardization method is constructed to achieve the same magnitude relationship between the standardized indicators and the market status under the premise of eliminating the dimensional difference; the construction method is as follows:

[0104] Positive correlation: x ij =(x ij -min i x ij ) / (max i x ij -min i x ij );

[0105] Negative correlation: x ij =(max i x i -x ij ) / (max i x ij -min i x ij ).

[0106] 3. The indicator score conversion module, based on the indicator standardization module, realizes the mapping of the original indicator value to the [0,1] interval; in actual business, the evaluation is often based on a percentage system, so it is necessary to perform weighting on this basis, including:

[0107] [50,100]:

[0108] [0,100]:

[0109] 4. The indicator merging weight module is used to calculate the indicators and weight them;

[0110] The indicator weights use principal component analysis (PCA) and factor analysis as optional indicator measurement methods.

[0111] The eigenvector corresponding to the maximum eigenvalue is used for weighting. The larger the eigenvalue of the covariance matrix, the larger the variance of the corresponding eigenvector direction, and the more original feature information it represents. Therefore, the direction corresponding to the maximum eigenvalue is the direction with the largest variance. Each component of the eigenvector corresponds to the rotation component of the original variable, so the weighted new data is:

[0112]

[0113] where γ 1 Represents the eigenvector corresponding to the maximum eigenvalue, that is, the score of the first principal component on the original index.

[0114] 5. The comprehensive score calculation module is based on the calculation results of the indicator merging weight module, and linearly transforms the indicator score to obtain the comprehensive score vector of the market status, which is recorded as:

[0115]

[0116] in Represents the weight result obtained based on statistical analysis of data.

[0117] 6. The market status threshold calculation module uses the estimated Gaussian mixture distribution results to determine the threshold, and refers to the number of intervals of the market status to determine the threshold division standard;

[0118] In the first step, the parameters of K Gaussian distributions are estimated by the EM algorithm. Assume that each Gaussian distribution is represented in ascending order of mean:

[0119] The second step is to determine the boundaries of each normal distribution according to the fluctuation size of each unit mean, and then calculate the fluctuation multiple:

[0120]

[0121] The third step is to determine the left threshold of the first Gaussian distribution and the right threshold of the kth Gaussian distribution, that is, the last Gaussian distribution, without using the fluctuation multiple; as well as the boundary of the intersection of two adjacent Gaussian distributions;

[0122] When K = 3, there are two results for determining the threshold, namely [μ1 -σ 1 , μ 1 +c 1 σ 1 , μ 2 +c 2 σ| 2 , μ 3 +σ 3 ]; [μ 1 -σ 1 , μ 1 +c 1 σ 1 , μ 3 -c 2 σ 3 , μ 3 +σ 3 ];

[0123] The fourth step is to judge the market status based on the threshold interval calculated in the third step; the method is interval mapping.

[0124] Through various data collection methods, we collect indicator data that can reflect the market status;

[0125] Check and calibrate the indicator data to ensure that there are no missing or abnormal data;

[0126] Input the data into the indicator standardization module to complete the data standardization;

[0127] Input the standardized data into the indicator score conversion module to complete the score calculation of the data indicator;

[0128] Input the indicator scores into the indicator combined weight module to complete the calculation of indicator weights;

[0129] Input the index scores and index weights into the comprehensive score calculation module to complete the calculation of the comprehensive score;

[0130] Input the comprehensive score into the market status threshold calculation module to complete the market status threshold calculation;

[0131] The comprehensive score and the market status threshold are combined to obtain the market status corresponding to the comprehensive score.

[0132] The embodiment of the present invention further provides a device for evaluating the market status of fast moving consumer goods, comprising: at least one memory and at least one processor;

[0133] The at least one memory is used to store a machine-readable program;

[0134] The at least one processor is used to call the machine-readable program to implement the method for evaluating the market status of fast-moving consumer goods described in the above embodiment.

[0135] The embodiment of the present invention further provides a computer-readable medium, on which computer instructions are stored, and when the computer instructions are executed by a processor, the processor executes the method for evaluating the market status of fast-moving consumer goods described in the above embodiment. Specifically, a system or device equipped with a storage medium can be provided, on which software program codes for implementing the functions of any of the above embodiments are stored, and a computer (or CPU or MPU) of the system or device reads and executes the program code stored in the storage medium.

[0136] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.

[0137] The storage medium embodiments for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer by a communication network.

[0138] In addition, it should be clear that the functions of any of the above embodiments can be implemented not only by executing the program code read by the computer, but also by enabling an operating system operating on the computer to complete part or all of the actual operations based on instructions from the program code.

[0139] In addition, it can be understood that the program code read from the storage medium is written to a memory provided in an expansion board inserted into the computer or written to a memory provided in an expansion unit connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or the expansion unit is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above-mentioned embodiments.

[0140] The present invention is shown and described in detail above through the accompanying drawings and preferred embodiments. However, the present invention is not limited to these disclosed embodiments. Based on the above multiple embodiments, those skilled in the art can know that the code review methods in the above different embodiments can be combined to obtain more embodiments of the present invention, and these embodiments are also within the protection scope of the present invention.

Claims

1. A method for evaluating the market status of fast-moving consumer goods, characterized in that: The evaluation of the market status of fast-moving consumer goods is realized based on a multi-dimensional weighted fitting model. The implementation of this method includes: 1) Data collection: collect data from multiple channels online and offline, and derive collection indicators from consumption and inventory records to build a complete indicator system; 2) Indicator standardization: Based on the positive and negative relationship between the collected indicators and the market status, a standardization method is constructed to achieve the same magnitude relationship between the standardized indicators and the market status while eliminating the dimensional differences; 3) Indicator score conversion, based on the indicator standardization, to achieve the mapping of the original indicator value to the [0,1] interval; 4) Merge the weights of indicators, calculate indicators, and weight the indicators; 5) Calculation of comprehensive score: based on the calculation result of the combined weight of the indicators, linear transformation is performed on the indicator scores to obtain a comprehensive score vector of the market status; 6) Market status threshold measurement, using the estimated Gaussian mixture distribution results to determine the threshold, and referring to the number of market status intervals to determine the threshold division standard.

2. A method for evaluating the market status of fast-moving consumer goods according to claim 1, characterized in that: The collected indicators include: market size, market growth rate, consumer loyalty, price sensitivity, inventory turnover rate, gross profit margin, and consumer satisfaction indicators.

3. The method for evaluating the market status of fast-moving consumer goods according to claim 1, characterized in that: The indicator standardization and the construction standardization method are as follows: Positive correlation: x ij =(x ij -min i x ij ) / (max i x ij -min i x ij ); Negative correlation: x ij =(max i x i -x ij ) / (max i x ij -min i x ij ).

4. The method for evaluating the market status of fast-moving consumer goods according to claim 1, characterized in that: When the indicator score conversion is evaluated in percentage in actual business, it is necessary to perform weighting based on the above mapping, including: [50,100]： [0,100]： 5. The method for evaluating the market status of fast-moving consumer goods according to claim 1, characterized in that: The indicators are combined with weights, The indicator measurement methods include the use of principal component analysis and factor analysis for indicator weights; The eigenvector corresponding to the maximum eigenvalue is used for weighting, because the maximum eigenvalue corresponds to the direction in which the variance of the original variable is the largest after projection, and each component of the eigenvector corresponds to the rotation component of the original variable, so the weighted new data is: Among them, γ1 represents the eigenvector corresponding to the maximum eigenvalue, that is, the score of the first principal component on the original index.

6. The method for evaluating the market status of fast-moving consumer goods according to claim 1, characterized in that: The market status comprehensive score vector is recorded as: in Represents the weight result obtained based on statistical analysis of data.

7. The method for evaluating the market status of fast-moving consumer goods according to claim 1, characterized in that: The market status threshold calculation includes the following steps: In the first step, the parameters of K Gaussian distributions are estimated by the EM algorithm. Assume that each Gaussian distribution is represented in ascending order of mean: The second step is to determine the boundaries of each normal distribution according to the fluctuation size of each unit mean, and then calculate the fluctuation multiple: The third step is to determine the left threshold of the first Gaussian distribution and the right threshold of the kth Gaussian distribution, that is, the last Gaussian distribution, without using the fluctuation multiple; as well as the boundary of the intersection of two adjacent Gaussian distributions; When K=3, there are two results in determining the threshold, namely [μ1-σ1, μ1+c1σ1, μ2+c2σ|2, μ3+σ3]; [μ1-σ1, μ1+c1σ1, μ3-c2σ3, μ3+σ3]; The fourth step is to judge the market status based on the threshold interval calculated in the third step; the method is interval mapping.

8. A fast-moving consumer goods market status evaluation system, characterized in that: include: The data collection module is used to collect data from multiple channels online and offline, and to derive collection indicators from consumption and inventory records, thus building a complete indicator system as a whole; The indicator standardization module builds a standardization method based on the positive and negative relationship between the collected indicators and the market status, and achieves the same magnitude relationship between the standardized indicators and the market status under the premise of eliminating the dimensional differences; The indicator score conversion module, based on the indicator standardization module, realizes the mapping of the original indicator value to the [0,1] interval; The indicator merging weight module is used to measure indicators and weight them; The comprehensive score calculation module performs linear transformation on the indicator score based on the calculation result of the indicator merging weight module to obtain the comprehensive score vector of the market status; The market status threshold calculation module uses the estimated Gaussian mixture distribution results to determine the threshold, and refers to the number of intervals of the market status to determine the threshold division standard; The system specifically implements the evaluation of the market status of fast-moving consumer goods through the method described in any one of claims 1 to 7.

9. A device for evaluating the market status of fast-moving consumer goods, characterized in that: include: at least one memory and at least one processor; The at least one memory is used to store a machine-readable program; The at least one processor is used to call the machine-readable program to implement the method described in any one of claims 1 to 7.

10. A computer-readable medium, characterized in that The computer readable medium stores computer instructions, which, when executed by a processor, can implement the method described in any one of claims 1 to 7.

Images