Enterprise marketing prediction management system based on Internet of Things data

Abstract

The invention relates to the technical field of business management, and discloses an enterprise marketing prediction management system based on Internet of Things data. Comprising the steps of screening out commodity transaction data under a screening condition, collecting comprehensive transaction data of the commodity transaction data, generating a transaction success index, judging whether a transaction positive prompt is generated or not, generating a transaction success difference value and a commodity marketing mode in combination with the transaction success index and a preset transaction success threshold value, and marketing the commodity according to the commodity marketing mode. Formulating a commodity marketing instruction; compared with the prior art, the comprehensive transaction data influencing the marketing transaction success rate can be accurately collected, the transaction success index of the commodity can be accurately calculated based on the comprehensive transaction data, the marketing prospect of the commodity in the market can be accurately judged and predicted, and meanwhile, a proper marketing mode is selected according to the predicted marketing prospect. And a corresponding marketing instruction is formulated to ensure that the commodity can realize a higher transaction success rate on the market, so that the sales volume of the commodity is improved.

Description

Technical Field

[0001] The present invention relates to the field of business management technology, and more specifically, to an enterprise marketing forecasting management system based on Internet of Things data. Background Art

[0002] Predicting product marketing through IoT data is an important basis for making business decisions and is also the foundation for carrying out other business forecasting operations. Especially before a company develops new products and promotes them in the market, it is necessary to predict the future marketing data of the products in the market through IoT data. Based on the predicted marketing transaction data, it can help the company to better formulate subsequent plans, thereby improving the transaction success rate of the products and increasing marketing revenue.

[0003] The Chinese patent application with application publication number CN117217814A discloses a sales forecasting method based on deep learning, which is based on the idea of ​​ensemble learning stacking and establishes a combined model including CNN, GRU, and MLP; wherein the CNN model is used to extract spatial information of data features, the GRU model is used to extract time series information of data features, and the MLP model is used to fuse feature information; the mean square error MSE is used as the loss function to train the input processed data set to obtain the corresponding sales forecast value; based on historical sales data and external influencing factors, by combining deep learning algorithm models, the effect of predicting sales volume in the future period is achieved;

[0004] The prior art has the following deficiencies:

[0005] The existing forecasting and analysis system manually collects a large amount of virtual transaction data of commodities in the market, summarizes and analyzes the large amount of transaction data to obtain analysis results, and predicts the marketing situation of commodities based on the analysis results. Due to the large amount of virtual transaction data and the complex types, when a large amount of multi-type data is summarized and analyzed, data calculation errors are prone to occur, resulting in inaccurate commodity marketing forecast results, and then it is impossible to formulate appropriate marketing instructions based on the actual forecast results, and it is impossible to greatly improve the success rate of commodity transactions and the marketing amount of commodities.

[0006] In view of this, the present invention proposes an enterprise marketing forecasting management system based on Internet of Things data to solve the above problems. Summary of the invention

[0007] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: an enterprise marketing forecasting management system based on Internet of Things data, applied to a data server, comprising:

[0008] The data screening module screens the historical business data in the database under the screening conditions and screens out the commodity transaction data;

[0009] A data collection module collects comprehensive transaction data of commodity transaction data and generates a transaction success index based on the comprehensive transaction data;

[0010] A comparison analysis module compares the transaction success index with a preset transaction success threshold, and determines whether to generate a positive transaction prompt based on the comparison result;

[0011] The marketing model module combines the transaction success index with the preset transaction success threshold to generate a transaction success difference, and generates a product marketing model based on the transaction success difference;

[0012] The marketing instruction module formulates commodity marketing instructions corresponding to the commodity marketing models according to different commodity marketing models.

[0013] Furthermore, the screening conditions are: the keywords in an independent business data need to include one or more of the promotion time, consultation time, word-of-mouth feedback, and simulated transaction;

[0014] The methods for screening commodity transaction data include:

[0015] Arrange the historical business data in the database in the order of the time when the data was formed to form a number of independent business data;

[0016] Process business data through natural language processing technology to identify keywords in each business data;

[0017] Keywords in commercial data are screened, and commercial data containing keywords such as promotion time, consultation time, word-of-mouth feedback, or simulated transactions are marked as commodity transaction data.

[0018] Furthermore, the comprehensive transaction data includes the promotion time excess, consultation time change value, excellent reputation interval value and simulated transaction success rate;

[0019] Methods for obtaining the excess promotion time include:

[0020] Obtain i commodity transaction data including promotion time from the database, and mark the start time and end time of the i promotion time respectively;

[0021] After comparing the difference between i starting times and i ending times, we can get i promotion durations;

[0022] The expression of the promotion duration is:

[0023] XC sci =SK zmi -SKqsi ;

[0024] In the formula, XC sci is the duration of the i-th promotion, SK zmi For the i-th final moment, SK qsi is the i-th starting time;

[0025] After comparing the i promotion durations with the standard promotion duration one by one, i duration differences are obtained;

[0026] The expression for the duration difference is:

[0027] SC czi =XC sci -BZ s ;

[0028] In the formula, SC czi is the i-th duration difference, BZ sc It is the standard promotion duration;

[0029] Remove the maximum and minimum values ​​of the duration difference, add up the remaining i-2 duration differences and calculate the average to obtain the excess of promotion time;

[0030] The expression for the promotion time excess is:

[0031]

[0032] In the formula, SC ce To promote the time overrun, SC cza is the ath duration difference.

[0033] Furthermore, the method for obtaining the positive consultation ratio includes:

[0034] Obtain p commodity transaction data including consultation time from the database, and mark the start time and end time of the p consultation time respectively;

[0035] After comparing the differences between the p start times and the p end times, p consultation durations are obtained;

[0036] The expression for consultation duration is:

[0037] XC zxp =SK jsp -SK ksp ;

[0038] In the formula, XC zxp is the pth consultation duration, SK jsp is the pth ending time, SK ksp is the pth starting time;

[0039] Record m consultation durations that are greater than or equal to the preset consultation threshold as positive durations, where m is less than p, and obtain m positive durations;

[0040] After accumulating the m positive durations, compare them with the total duration of the p consultation durations to obtain the positive consultation ratio;

[0041] The expression of the positive consultation ratio is:

[0042]

[0043] In the formula, ZX zx is the proportion of positive consultations, SC zxb is the bth positive duration, XC zxc This is the duration of the cth consultation.

[0044] Furthermore, the method for obtaining the excellent word-of-mouth interval value includes:

[0045] Obtain k commodity transaction data containing word-of-mouth feedback through the database, and summarize k word-of-mouth values ​​one by one;

[0046] Number the k reputation values ​​in sequence, and mark w reputation values ​​as the numbers of excellent reputations, where w is less than k;

[0047] Count the number of numbers between two adjacent excellent reputations one by one to obtain w-1 sub-interval values;

[0048] The w-1 sub-interval values ​​are accumulated and averaged to obtain the excellent reputation interval value;

[0049] The expression of the excellent reputation interval value is:

[0050]

[0051] In the formula, JG yx is the excellent reputation interval value, JG zd is the dth subinterval value.

[0052] Furthermore, the method for obtaining the success rate of simulated transactions includes:

[0053] A1: Obtain q commodity transaction data including simulated transactions from the database, and identify the simulated transaction status of the q commodity transaction data;

[0054] A2: Record the commodity transaction data with successful simulated transaction status as successful data, and count the number of successful data;

[0055] A3: Compare the number of successful data with the transaction data of q commodities to obtain the sub-transaction success rate;

[0056] A4: Repeat steps A1-A3 r times to obtain r sub-transaction success rates;

[0057] The expression of sub-transaction success rate is:

[0058]

[0059] In the formula, JY cgr is the success rate of the rth sub-transaction, SL cgr is the number of r-th successful data;

[0060] A5: Add up the success rates of r sub-transactions and find the average to get the standard success rate;

[0061] The expression of standard success rate is:

[0062]

[0063] In the formula, BZ cg is the standard success rate, JY cge is the success rate of the e-th sub-transaction;

[0064] A6: Record the sub-transaction success rate that is lower than the standard success rate as the effective success rate, and obtain h effective success rates, where h is less than r. Add up the h effective success rates and find the average to obtain the simulated transaction success rate.

[0065] The expression of simulated transaction success rate is:

[0066]

[0067] In the formula, MN cg To simulate the transaction success rate, YX cgf is the fth effective success rate.

[0068] Furthermore, the expression of the transaction success index is:

[0069]

[0070] In the formula, CG zs is the transaction success index, is the weight factor;

[0071] The determination method of whether to generate a positive transaction reminder includes:

[0072] The transaction success index CG zs The preset transaction success threshold CG yz Make a difference comparison;

[0073] When CG zs Greater than or equal to CG yz When the transaction is positively prompted, it is determined that the transaction is positively prompted;

[0074] When CG zs Smaller than CG yz When the transaction is positively prompted, it is determined that no positive transaction prompt will be generated.

[0075] Furthermore, the expression of the transaction success difference is:

[0076] CG cz =CG zs -CG yz ;

[0077] In the formula, CG cz The difference in transaction success;

[0078] Commodity marketing models include conventional marketing models and aggressive marketing models;

[0079] The methods for generating conventional marketing models and aggressive marketing models include:

[0080] The transaction success difference CG cz and standard deviation threshold CG bz Compare;

[0081] When CG cz Greater than CG bz When, generate aggressive marketing mode;

[0082] When CG cz Less than or equal to CG bz Generate a regular marketing model.

[0083] Furthermore, the commodity marketing instructions include a single-point marketing instruction for opening one marketing point in one marketing area and a multi-point marketing instruction for opening at least two marketing points in one marketing area;

[0084] The method for formulating a single-point marketing instruction for opening one marketing point in a marketing area and a multi-point marketing instruction for opening at least two marketing points in a marketing area includes:

[0085] When in regular marketing mode, formulate a single-point marketing instruction to open a marketing point within a marketing area;

[0086] When in aggressive marketing mode, formulate multi-point marketing instructions by opening at least two marketing points in a marketing area.

[0087] Technical effects and advantages of an enterprise marketing forecasting management system based on Internet of Things data of the present invention:

[0088] The present invention screens historical commercial data in a database under screening conditions to screen out commodity transaction data, collects comprehensive transaction data of the commodity transaction data, generates a transaction success index based on the comprehensive transaction data, compares the transaction success index with a preset transaction success threshold, determines whether to generate a positive transaction prompt based on the comparison result, generates a transaction success difference by combining the transaction success index with the preset transaction success threshold, generates a commodity marketing model based on the transaction success difference, and formulates commodity marketing instructions corresponding to the commodity marketing model according to different commodity marketing models; compared with the prior art, the present invention can accurately collect comprehensive transaction data that affects the success rate of marketing transactions, accurately calculate the transaction success index of the commodity based on the comprehensive transaction data, accurately judge and predict the marketing prospects of the commodity in the market after comparing and analyzing the transaction success index with the preset transaction success threshold, and select a suitable marketing model according to the predicted marketing prospects, and formulate corresponding marketing instructions to ensure that the commodity can achieve a higher transaction success rate in the market, thereby increasing the marketing amount of the commodity. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] Figure 1 A schematic diagram of an enterprise marketing forecasting management system based on Internet of Things data provided by Embodiment 1 of the present invention;

[0090] Figure 2 A flowchart of a method for enterprise marketing forecasting management based on Internet of Things data provided in Embodiment 2 of the present invention;

[0091] Figure 3 A schematic diagram of a structural diagram of an electronic device provided in Embodiment 3 of the present invention;

[0092] Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0093] 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.

[0094] Example 1: Please refer to Figure 1 As shown, the enterprise marketing forecasting management system based on Internet of Things data described in this embodiment is applied to a data server, including:

[0095] The data screening module screens the historical business data in the database under the screening conditions and screens out the commodity transaction data;

[0096] Historical business data refers to a collection of data about different life cycles of commodity manufacturing, procurement, trading and after-sales service stored in a database, which is used to accurately represent the entire life cycle of commodities, so as to provide users with subsequent query and browsing operations. Due to the complexity and diversity of historical business data, different types of business data may contain commodity information with different meanings. Therefore, in order to facilitate the subsequent rapid and accurate collection of information related to commodity transactions, it is necessary to filter historical business data based on the filtering conditions, so as to obtain commercial data that can be directly used and only contains the life cycle of information related to commodity transactions, and such commercial data is called commodity transaction data;

[0097] When screening historical business data and obtaining commodity transaction data, it is necessary to meet the pre-set screening conditions to ensure the accuracy and reliability of commodity transaction data;

[0098] The screening conditions are as follows: the keywords in an independent business data need to include one or more of the following: promotion time, consultation time, word-of-mouth feedback, and simulated transaction;

[0099] The methods for screening commodity transaction data include:

[0100] Arrange the historical business data in the database in the order of the time when the data was formed to form a number of independent business data;

[0101] Process business data through natural language processing technology to identify keywords in each business data;

[0102] Filter keywords in commercial data and mark commercial data containing keywords such as promotion time, consultation time, word-of-mouth feedback, or simulated transactions as commodity transaction data;

[0103] A data collection module collects comprehensive transaction data of commodity transaction data and generates a transaction success index based on the comprehensive transaction data;

[0104] Comprehensive transaction data refers to comprehensive data that can affect whether a commodity can be successfully traded. Since the success of a commodity transaction depends not only on the quality of the commodity itself, but also on the market's recognition of the commodity and the amount of investment in marketing and publicity, comprehensive transaction data can provide data support for the probability of successful commodity transactions in the market and serve as the basis for predicting the success of commodity transactions;

[0105] Comprehensive transaction data includes the promotion time excess, consultation time change value, excellent reputation interval value and simulated transaction success rate;

[0106] The excess of promotion time refers to the extent to which the promotion time spent by marketers in order to promote products to the market and increase the degree of awareness of the products in the market exceeds the standard promotion time. The greater the excess of promotion time, the more time marketers spend to effectively promote the products. At this time, the market's understanding and cognition of the products is deeper, the higher the probability of successful product transactions, and the greater the transaction success index;

[0107] Methods for obtaining the excess promotion time include:

[0108] Obtain i commodity transaction data including promotion time from the database, and mark the start time and end time of the i promotion time respectively;

[0109] After comparing the difference between l starting times and i ending times, we can get i promotion durations;

[0110] The expression of the promotion duration is:

[0111] XC sci =SK zmi -SK qsi ;

[0112] In the formula, XC sci is the duration of the i-th promotion, SK zmi For the i-th final moment, SK qsi is the i-th starting time;

[0113] After comparing the i promotion durations with the standard promotion duration one by one, i duration difference values ​​are obtained; the standard promotion duration refers to the ideal promotion duration set by the marketer for the promotion time of the product in advance, which can provide a comparison basis for the promotion duration of the product, accurately compare whether the actual product promotion duration is lower or higher than the ideal promotion duration, and use it to obtain the difference between the actual product promotion duration and the ideal promotion duration; the standard promotion duration is obtained by collecting a large number of historical minimum actual promotion durations of the same type of products and optimizing the coefficients;

[0114] The expression for the duration difference is:

[0115] SC czi =XC sci -BZ sc ;

[0116] In the formula, SC czi is the i-th duration difference, BZ sc It is the standard promotion duration;

[0117] Remove the maximum and minimum values ​​of the duration difference, add up the remaining i-2 duration differences and calculate the average to obtain the excess of promotion time;

[0118] The expression for the promotion time excess is:

[0119]

[0120] In the formula, SC ce To promote the time overrun, SC cza is the ath duration difference;

[0121] The positive consultation ratio refers to the ratio of the time spent by marketers in communicating with potential customers and consulting about the product itself to the total time. The larger the positive consultation ratio, the longer the potential customer spends consulting about the product itself. At this time, the more interested the potential customer is in the product, the higher the probability of successful product transaction and the greater the transaction success index.

[0122] The methods for obtaining the positive consultation ratio include:

[0123] Obtain p commodity transaction data including consultation time from the database, and mark the start time and end time of the p consultation time respectively;

[0124] After comparing the differences between the p start times and the p end times, p consultation durations are obtained;

[0125] The expression for consultation duration is:

[0126] XC zxp =SK jsp -SK ksp ;

[0127] In the formula, XC zxp is the pth consultation duration, SK jsp is the pth ending time, SK ksp is the pth starting time;

[0128] Record m consultation durations that are greater than or equal to the preset consultation threshold as positive durations, where m is less than p, and obtain m positive durations; the preset consultation threshold is used to determine the length of time that potential customers spend consulting on products, thereby dividing the consultation duration of potential customers into positive duration and reverse duration, where positive duration indicates that the consultation duration of potential customers on products is longer, and reverse duration indicates that the consultation duration of potential customers on products is shorter. The preset consultation threshold is obtained by collecting a large number of historical consultation durations of products of the same type, and combining it with the market environment in which the marketers are located, and after multiple debugging;

[0129] After accumulating the m positive durations, compare them with the total duration of the p consultation durations to obtain the positive consultation ratio;

[0130] The expression of the positive consultation ratio is:

[0131]

[0132] In the formula, ZX zx is the proportion of positive consultations, SC zxb is the bth positive duration, XC zxc is the duration of the cth consultation;

[0133] The excellent word-of-mouth interval value refers to the interval range of word-of-mouth feedback from market users after market research. The larger the excellent word-of-mouth interval value, the larger the interval range of excellent word-of-mouth feedback. At this time, the frequency of excellent word-of-mouth is lower, the market's recognition of the product is lower, the probability of successful product transactions is lower, and the transaction success index is smaller.

[0134] Methods for obtaining excellent word-of-mouth interval values ​​include:

[0135] Obtain k commodity transaction data containing word-of-mouth feedback through the database, and summarize k word-of-mouth values ​​one by one; the word-of-mouth value refers to the commodity transaction data containing word-of-mouth feedback information, which is used to indicate the specific word-of-mouth situation of the commodity transaction data. The word-of-mouth value includes excellent word-of-mouth, good word-of-mouth, general word-of-mouth and negative word-of-mouth; among them, excellent word-of-mouth means that the reputation of the commodity is very good, good word-of-mouth means that the reputation of the commodity is good, general word-of-mouth means that the reputation of the commodity is in the middle, and negative word-of-mouth means that the reputation of the commodity is not good;

[0136] Number the k reputation values ​​in sequence, and mark w reputation values ​​as the numbers of excellent reputations, where w is less than k;

[0137] Count the number of numbers between two adjacent excellent reputations one by one to obtain w-1 sub-interval values;

[0138] The w-1 sub-interval values ​​are accumulated and averaged to obtain the excellent reputation interval value;

[0139] The expression of the excellent reputation interval value is:

[0140]

[0141] In the formula, JG yx is the excellent reputation interval value, JG zd is the dth sub-interval value;

[0142] It should be noted that in order to avoid the situation where the excellent word-of-mouth interval value is 0, when obtaining commodity transaction data containing word-of-mouth feedback from the database, the word-of-mouth value of the commodity transaction data must contain at least 3 excellent word-of-mouth, so as to ensure that the subsequent calculation of the excellent word-of-mouth interval value will not be 0, thereby improving the calculation accuracy of the data;

[0143] The simulated transaction success rate refers to the ratio of the number of successful commodity transactions to the number of transactions when the marketer conducts simulated marketing of the commodity in the market before officially starting to market the commodity. The higher the simulated transaction success rate, the higher the probability of successful transactions during the simulated marketing of the commodity, and the greater the transaction success index;

[0144] Methods for obtaining the success rate of simulated transactions include:

[0145] A1: Obtain q commodity transaction data including simulated transactions from a database, and identify the simulated transaction status of the q commodity transaction data; the simulated transaction status refers to the final transaction status of the simulated transaction, and the simulated transaction status includes transaction success and transaction failure, wherein a transaction success indicates that the commodity is successfully sold during the simulated transaction, and a transaction failure indicates that the commodity is not successfully sold during the simulated transaction;

[0146] A2: Record the commodity transaction data with successful simulated transaction status as successful data, and count the number of successful data;

[0147] A3: Compare the number of successful data with the transaction data of q commodities to obtain the sub-transaction success rate;

[0148] A4: Repeat steps A1-A3 r times to obtain r sub-transaction success rates;

[0149] The expression of sub-transaction success rate is:

[0150]

[0151] In the formula, JY cgr is the success rate of the rth sub-transaction, SL cgr is the number of r-th successful data;

[0152] A5: Add up the success rates of r sub-transactions and find the average to get the standard success rate;

[0153] The expression of standard success rate is:

[0154]

[0155] In the formula, BZ cg is the standard success rate, JY cge is the success rate of the e-th sub-transaction;

[0156] A6: The sub-transaction success rate that is lower than the standard success rate is recorded as the effective success rate, and h effective success rates are obtained, where h is less than r. The h effective success rates are accumulated and averaged to obtain the simulated transaction success rate. By recording the sub-transaction success rate that is lower than the standard success rate as the effective success rate, the sub-transaction success rate with a large value can be removed, thereby reducing the value of the simulated transaction success rate. On the one hand, the number of sub-transaction success rates can be reduced and the calculation rate can be increased. On the other hand, the simulated transaction success rate can also be reduced, avoiding the error caused by the rapid successful transaction of a large number of commodities due to the market recovery in a short period of time, thereby playing a role in numerical compensation for the simulated transaction success rate and further improving the accuracy of the simulated transaction success rate.

[0157] The expression of simulated transaction success rate is:

[0158]

[0159] In the formula, MN cg To simulate the transaction success rate, YX cgf is the fth effective success rate;

[0160] The transaction success index refers to the numerical representation of the marketer's ability to successfully market a product in the market. The larger the transaction success index, the higher the market acceptance of the product, and the easier it is to trade the product.

[0161] The expression of transaction success index is:

[0162]

[0163] In the formula, CG zs is the transaction success index, is the weight factor;

[0164] in, For example, is 0.22, is 0.28, is 0.37, is 0.13;

[0165] In addition, it should be noted that the size of the weight factor is a specific value obtained by quantifying each data, which is convenient for subsequent comparison. The size of the weight factor depends on the amount of comprehensive transaction data and the initial setting of the corresponding weight factor for each set of comprehensive transaction data by those skilled in the art;

[0166] A comparison analysis module compares the transaction success index with a preset transaction success threshold, and determines whether to generate a positive transaction prompt based on the comparison result;

[0167] The positive transaction prompt is used as a result of comparing the transaction success index with the preset transaction success threshold, and provides the marketer with the transaction success information of the product based on the final result of the comparison. When a positive transaction prompt is generated, it means that the probability of the product transaction success is high, and the product can be put on the market. When a positive transaction prompt is not generated, it means that the probability of the product transaction success is low, and the product needs to be put on the market with caution.

[0168] The determination method of whether to generate a positive transaction reminder includes:

[0169] The transaction success index CG zs The preset transaction success threshold CG yz Compare the difference; the preset transaction success threshold is used to distinguish the size of the commodity transaction success index, and as the standard size of the transaction success index, the transaction success index can be divided into the range of generating a positive transaction prompt or not generating a positive transaction prompt. The preset transaction success threshold is obtained by collecting a large number of historical commodity transaction success indexes and optimizing the coefficient;

[0170] When CG zs Greater than or equal to CG yz , it means that the transaction success index is greater than or equal to the preset transaction success threshold. At this time, the probability of successful commodity transaction is high, and a positive transaction prompt is generated;

[0171] When CG zs Smaller than CG yz , it means that the transaction success index is less than the preset transaction success threshold. At this time, the probability of successful commodity transaction is low, and it is determined that no positive transaction prompt will be generated;

[0172] The marketing model module combines the transaction success index with the preset transaction success threshold to generate a transaction success difference, and generates a product marketing model based on the transaction success difference;

[0173] The transaction success difference is used to indicate the difference between the transaction success index and the preset transaction success threshold. When a positive transaction prompt is generated, it means that the transaction success index is greater than or equal to the preset transaction success threshold, so that there is a data difference between the two.

[0174] The expression of transaction success difference is:

[0175] CG cz =CG zs -CG yz ;

[0176] In the formula, CG cz The difference in transaction success;

[0177] Product marketing model refers to the different types of marketing methods formulated by marketers based on the size of the transaction success difference when generating positive transaction prompts, so that products can match corresponding marketing methods within the range of different transaction success difference values, thereby improving the transaction success rate of products and further increasing the marketing amount of products;

[0178] Product marketing models include conventional marketing models and aggressive marketing models. Conventional marketing models are general marketing methods that are formulated in line with market conditions when the difference in transaction success is small, so as to ensure that products can be marketed stably according to market conditions. Aggressive marketing models are advanced marketing methods that are formulated in excess of market conditions when the difference in transaction success is large. Aggressive marketing models are based on good market conditions and are combined with the marketer's strong stress resistance and marketing capabilities to achieve marketing of products that exceed market expectations and maximize the sales of products.

[0179] The methods for generating conventional marketing models and aggressive marketing models include:

[0180] The transaction success difference CG cz and standard deviation threshold CG bz Comparison; The standard deviation threshold is a numerical basis for distinguishing the size of the transaction success difference, so that the transaction success difference can be divided into a lower range and a higher range, and the conventional marketing model and the aggressive marketing model can be effectively distinguished. The standard deviation threshold is obtained by collecting a large number of historical transaction success differences corresponding to the conventional marketing model and the aggressive marketing model, and then optimizing the coefficient;

[0181] When CG cz Greater than CG bz When , it means that the transaction success difference is greater than the standard difference threshold. At this time, the marketing prospect of the product in the market is good, and an aggressive marketing mode is generated;

[0182] When CG cz Less than or equal to CG bz When , it means that the transaction success difference is less than or equal to the standard difference threshold. At this time, the marketing prospect of the product in the market is average, and a conventional marketing model is generated;

[0183] The marketing instruction module formulates commodity marketing instructions corresponding to the commodity marketing models according to different commodity marketing models;

[0184] Product marketing instructions refer to the specific measures and means of marketing products in the market formulated under different product marketing models, so that products can be traded in the market reasonably and controllably under different product marketing models, thereby increasing the transaction success rate of products and thus increasing marketing revenue;

[0185] Product marketing instructions include single-point marketing instructions for opening one marketing point in a marketing area and multi-point marketing instructions for opening at least two marketing points in a marketing area. The formulation of marketing areas is determined by the marketer according to the specific circumstances of the marketer's level. For example, a marketing area of ​​a first-level marketer is 50 kilometers in radius. It can also be determined according to the administrative level of the region, for example, a county-level administrative district is a marketing area.

[0186] The method for formulating a single-point marketing instruction for opening one marketing point in a marketing area and a multi-point marketing instruction for opening at least two marketing points in a marketing area includes:

[0187] When in the regular marketing mode, the marketer needs to ensure that the product can be marketed stably according to the market conditions to ensure that the marketer's sales will not fluctuate greatly. In this case, a marketing point is set up in a marketing area for single-point marketing instructions;

[0188] When in the aggressive marketing mode, the marketer needs to achieve a marketing effect that exceeds market expectations to ensure that the marketer's sales can be greatly increased in the short term. In this case, a multi-point marketing instruction is formulated to open at least two marketing points in a marketing area;

[0189] In this embodiment, by screening the historical business data in the database under the screening conditions, the commodity transaction data is screened out, the comprehensive transaction data of the commodity transaction data is collected, and a transaction success index is generated based on the comprehensive transaction data. The transaction success index is compared with a preset transaction success threshold, and based on the comparison result, it is determined whether to generate a positive transaction prompt, and a transaction success difference is generated by combining the transaction success index with the preset transaction success threshold. Based on the transaction success difference, a commodity marketing model is generated, and commodity marketing instructions corresponding to the commodity marketing model are formulated according to different commodity marketing models. Compared with the prior art, it is possible to accurately collect comprehensive transaction data that affects the success rate of marketing transactions, and accurately calculate the transaction success index of the commodity based on the comprehensive transaction data. After comparing and analyzing the transaction success index with the preset transaction success threshold, the marketing prospects of the commodity in the market can be accurately judged and predicted. At the same time, a suitable marketing model is selected according to the predicted marketing prospects, and corresponding marketing instructions are formulated to ensure that the commodity can achieve a higher transaction success rate in the market, thereby increasing the marketing amount of the commodity.

[0190] Example 2: Please refer to Figure 2 As shown, the part not described in detail in this embodiment is described in Example 1, which provides an enterprise marketing forecast management method based on Internet of Things data, which is applied to a data server and implemented based on an enterprise marketing forecast management system based on Internet of Things data, including:

[0191] S1: Under the screening conditions, the historical business data in the database is screened to select commodity transaction data;

[0192] S2: Collect comprehensive transaction data of commodity transaction data, and generate a transaction success index based on the comprehensive transaction data;

[0193] S3: comparing the transaction success index with a preset transaction success threshold, and determining whether to generate a positive transaction prompt based on the comparison result;

[0194] S4: combining the transaction success index with a preset transaction success threshold to generate a transaction success difference, and generating a product marketing model based on the transaction success difference;

[0195] S5: According to different commodity marketing models, formulate commodity marketing instructions corresponding to the commodity marketing models.

[0196] Example 3: Please refer to Figure 3 As shown, this embodiment discloses an electronic device, including a processor and a memory;

[0197] Wherein, the memory stores a computer program that can be called by the processor;

[0198] The processor executes the enterprise marketing forecasting management method based on Internet of Things data by calling the computer program stored in the memory.

[0199] Since the electronic device introduced in this embodiment is an electronic device used to implement a method for enterprise marketing forecasting management based on Internet of Things data in Example 2 of this application, based on the method for enterprise marketing forecasting management based on Internet of Things data introduced in the embodiment of this application, a person skilled in the art can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as a person skilled in the art implements the electronic device used in a method for enterprise marketing forecasting management based on Internet of Things data in the embodiment of this application, it belongs to the scope of protection of this application.

[0200] Example 4: Please refer to Figure 4 As shown, this embodiment discloses a computer-readable storage medium on which a rewritable computer program is stored;

[0201] When the computer program is run, it implements the enterprise marketing forecasting management method based on Internet of Things data.

[0202] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An enterprise marketing forecasting management system based on Internet of Things data, applied to a data server, characterized in that: include: The data screening module screens the historical business data in the database under the screening conditions and screens out the commodity transaction data; A data collection module collects comprehensive transaction data of commodity transaction data and generates a transaction success index based on the comprehensive transaction data; A comparison analysis module compares the transaction success index with a preset transaction success threshold, and determines whether to generate a positive transaction prompt based on the comparison result; The marketing model module combines the transaction success index with the preset transaction success threshold to generate a transaction success difference, and generates a product marketing model based on the transaction success difference; The marketing instruction module formulates commodity marketing instructions corresponding to the commodity marketing models according to different commodity marketing models.

2. According to claim 1, the enterprise marketing forecasting management system based on Internet of Things data is characterized in that: The screening condition is: the keywords in an independent business data need to include one or more of the following: promotion time, consultation time, word-of-mouth feedback, and simulated transaction; The methods for screening commodity transaction data include: Arrange the historical business data in the database in the order of the time when the data was formed to form a number of independent business data; Process business data through natural language processing technology to identify keywords in each business data; The keywords in the commercial data are filtered, and the commercial data containing keywords such as promotion time, consultation time, word-of-mouth feedback or simulated transactions are marked as commodity transaction data.

3. The enterprise marketing forecasting management system based on Internet of Things data according to claim 2 is characterized in that: The comprehensive transaction data includes the promotion time excess, consultation time change value, excellent reputation interval value and simulated transaction success rate; Methods for obtaining the excess promotion time include: Obtain i commodity transaction data including promotion time from the database, and mark the start time and end time of the i promotion time respectively; After comparing the difference between i starting times and i ending times, we can get i promotion durations; The expression of the promotion duration is: XC sci =SK zmi -SK qsi ; In the formula, XC sci is the duration of the i-th promotion, SK zmi For the i-th final moment, SK qsi is the i-th starting time; After comparing the i promotion durations with the standard promotion duration one by one, i duration differences are obtained; The expression of duration difference is: SC czi =XC sci -BZ sc ; In the formula, SC czi is the i-th duration difference, BZ sc It is the standard promotion duration; Remove the maximum and minimum values ​​of the duration difference, add up the remaining i-2 duration differences and calculate the average to obtain the excess of promotion time; The expression for the promotion time excess is: In the formula, SC ce To promote the time overrun, SC cza is the ath duration difference.

4. The enterprise marketing forecasting management system based on Internet of Things data according to claim 3 is characterized in that: The method for obtaining the positive consultation ratio value includes: Obtain p commodity transaction data including consultation time from the database, and mark the start time and end time of the p consultation time respectively; After comparing the differences between the p start times and the p end times, p consultation durations are obtained; The expression for consultation duration is: XC zxp =SK jsp -SK ksp ; In the formula, XC zxp is the pth consultation duration, SK jsp is the pth ending time, SK ksp is the pth starting time; Record m consultation durations that are greater than or equal to the preset consultation threshold as positive durations, where m is less than p, and obtain m positive durations; After accumulating the m positive durations, compare them with the total duration of the p consultation durations to obtain the positive consultation ratio; The expression of the positive consultation ratio is: In the formula, ZX zx is the proportion of positive consultations, SC zxb is the bth positive duration, XC zxc This is the Cth consultation duration.

5. The enterprise marketing forecasting management system based on Internet of Things data according to claim 4 is characterized in that: The method for obtaining the excellent word-of-mouth interval value includes: Obtain k commodity transaction data containing word-of-mouth feedback through the database, and summarize k word-of-mouth values ​​one by one; Number the k reputation values ​​in sequence, and mark w reputation values ​​as the numbers of excellent reputations, where w is less than k; Count the number of numbers between two adjacent excellent reputations one by one to obtain w-1 sub-interval values; The w-1 sub-interval values ​​are accumulated and averaged to obtain the excellent reputation interval value; The expression of the excellent reputation interval value is: In the formula, JG yx is the excellent reputation interval value, JG zd is the dth subinterval value.

6. The enterprise marketing forecasting management system based on Internet of Things data according to claim 5 is characterized in that: The method for obtaining the simulated transaction success rate includes: A1: Obtain q commodity transaction data including simulated transactions from the database, and identify the simulated transaction status of the q commodity transaction data; A2: Record the commodity transaction data with successful simulated transaction status as successful data, and count the number of successful data; A3: Compare the number of successful data with the transaction data of q commodities to obtain the sub-transaction success rate; A4: Repeat steps A1-A3 r times to obtain r sub-transaction success rates; The expression of sub-transaction success rate is: In the formula, JY cgr is the success rate of the rth sub-transaction, SL cgr is the number of r-th successful data; A5: Add up the success rates of r sub-transactions and calculate the average to get the standard success rate; The expression of standard success rate is: In the formula, BZ cg is the standard success rate, JY cge is the success rate of the e-th sub-transaction; A6: Record the sub-transaction success rate that is lower than the standard success rate as the effective success rate, and obtain h effective success rates, where h is less than r. Add up the h effective success rates and find the average to obtain the simulated transaction success rate. The expression of simulated transaction success rate is: In the formula, MN cg To simulate the transaction success rate, YX cgf is the fth effective success rate.

7. The enterprise marketing forecasting management system based on Internet of Things data according to claim 6 is characterized in that: The expression of the transaction success index is: In the formula, CG zs is the transaction success index, is the weight factor; The determination method of whether to generate a positive transaction reminder includes: The transaction success index CG zs The preset transaction success threshold CG yz Make a difference comparison; When CG zs Greater than or equal to CG yz When the transaction is positively prompted, it is determined that the transaction is positively prompted; When CG z s is less than CG yz When the transaction is positively prompted, it is determined that no positive transaction prompt will be generated.

8. The enterprise marketing forecasting management system based on Internet of Things data according to claim 7 is characterized in that: The expression of the transaction success difference is: CG cz =CG zs -CG yz ; In the formula, CG cz The difference in transaction success; Commodity marketing models include conventional marketing models and aggressive marketing models; The methods for generating conventional marketing models and aggressive marketing models include: The transaction success difference CG cz and standard deviation threshold CG bz Compare; When CG cz Greater than CG bz When, generate aggressive marketing mode; When CG cz Less than or equal to CG bz Generate a regular marketing model.

9. The enterprise marketing forecasting management system based on Internet of Things data according to claim 8, characterized in that: The commodity marketing instructions include a single-point marketing instruction for opening one marketing point within a marketing area and a multi-point marketing instruction for opening at least two marketing points within a marketing area; The method for formulating a single-point marketing instruction for opening one marketing point in a marketing area and a multi-point marketing instruction for opening at least two marketing points in a marketing area includes: When in regular marketing mode, formulate a single-point marketing instruction to open a marketing point within a marketing area; When in aggressive marketing mode, formulate multi-point marketing instructions by opening at least two marketing points in a marketing area.

Images