Potential truck customer information determination adaptive optimization method based on information entropy
Through an adaptive optimization method based on information entropy, the potential truck customer information determination model is optimized, which solves the problem that weight selection depends on experience in the prior art, and improves the accuracy and marketing success rate of information determination.
Patent Information
- Application Number
- CN202510116343.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-24
- Publication Date
- 2025-04-25
AI Technical Summary
When weighting processing of potential truck customer information in the prior art, weight selection depends on experience, resulting in insufficient accuracy in determining potential truck customer information, making it difficult to effectively attract truck fleets and drivers to choose to cross the sea in the port area.
Adaptive optimization method based on information entropy is adopted to construct marketing data sets, calculate the information gain of historical cross-sea characteristics to marketing results, determine the contribution ratio, and adjust the weight to optimize the potential truck customer information determination model.
It improves the accuracy of determining potential truck customer information, enhances the probability of success in marketing based on potential truck customer information, and helps the port area to form a differentiated competitive advantage in competition.
Smart Images
Figure CN119887283A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of data processing technology, and more specifically, relates to an adaptive optimization method for determining potential truck customer information based on information entropy. Background Art
[0002] As an important waterway in China, the Qiongzhou Strait connects Hainan Island and Guangdong Province. Its passenger and vehicle ferry transportation plays a vital role in promoting economic exchanges and personnel exchanges between the two places. At present, the passenger and vehicle ferry transportation in the Qiongzhou Strait has formed three main channels, namely "Xiuying Port-Haian New Port", "Xinhai Port-Xuwen Port" and "Nan Port-Bei Port". Although these three channels are separated from each other geographically, the crossing time and efficiency are basically the same, providing passengers with a variety of crossing options.
[0003] During the off-season of the passenger and vehicle ferry business, due to the relatively abundant supply of tickets, the ports are facing fierce competition, especially for truck fleets and truck drivers. However, due to the uniformity of ticket prices in the Qiongzhou Strait, it is difficult for each port to form differentiated competition in terms of pricing strategy. Therefore, how to mine potential truck customer information and formulate effective marketing strategies to attract fleets and drivers to choose this port area to cross the sea has become the key to increasing the company's revenue and enhancing market competitiveness.
[0004] The related technology provides a method for obtaining information on potential truck customers based on multi-source information mining and analysis. By assigning values and weighting data on the frequency of sea crossing, sea crossing port selection data and frequently transported cargo types of target sea crossing trucks in a recent historical time period, a quantitative result of the possibility of the target sea crossing truck choosing the target port to cross the sea within a target time period is obtained, thereby realizing the positioning of potential truck customers.
[0005] However, when weighting different influencing factors in this method, the weights are generally fixed values selected based on experience, and the accuracy of the quantitative results of the possibility of the target sea-crossing truck choosing the target port to cross the sea within the target time period needs to be improved. Summary of the invention
[0006] In view of the above-mentioned defects in the prior art, the present application provides an adaptive optimization method for determining potential truck customer information based on information entropy, aiming to solve the optimization problem of determining potential truck customer information.
[0007] In a first aspect, the present application provides an adaptive optimization method for determining potential truck customer information based on information entropy, comprising: Constructing a marketing data set of potential truck customers in the previous marketing time period, the marketing data set includes historical sea crossing feature values obtained by statistically analyzing historical sea crossing data of potential truck customers in the previous marketing time period and the marketing result values obtained by statistically analyzing actual sea crossing port data of potential truck customers in the previous marketing time period; Determine the information gain of various historical cross-sea features to the marketing results, and determine the contribution ratio of various historical cross-sea features to the marketing results based on the information gain; Adjust the weights of various quantified values of historical sea crossing data in the potential truck customer information determination model based on the contribution ratio to obtain an optimized potential truck customer information determination model; The potential truck customer information within the current marketing time period is determined based on the optimized potential truck customer information determination model.
[0008] In a second aspect, the present application further provides an adaptive optimization device for determining potential truck customer information based on information entropy, comprising: A construction module is used to construct a marketing data set of potential truck customers in the previous marketing time period, the marketing data set including historical sea crossing feature values obtained by statistically analyzing historical sea crossing data of potential truck customers in the previous marketing time period and the marketing result values obtained by statistically analyzing actual sea crossing port data of potential truck customers in the previous marketing time period; The first determination module is used to determine the information gain of various historical cross-sea features to the marketing results, and determine the contribution ratio of various historical cross-sea features to the marketing results based on the information gain; An optimization module is used to adjust the weights of the quantitative values of various historical sea crossing data in the potential truck customer information determination model based on the contribution ratio to obtain an optimized potential truck customer information determination model; The second determination module is used to determine the potential truck customer information within the current marketing time period based on the optimized potential truck customer information determination model.
[0009] In a third aspect, the present application also provides an electronic device, comprising: at least one memory for storing programs; and at least one processor for executing the programs stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method described in the first aspect or any possible implementation of the first aspect.
[0010] In a fourth aspect, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method described in the first aspect or any possible implementation of the first aspect.
[0011] In a fifth aspect, the present application further provides a computer program product, which, when executed on a processor, enables the processor to execute the method described in the first aspect or any possible implementation manner of the first aspect.
[0012] The present application provides an adaptive optimization method for determining potential truck customer information based on information entropy. By constructing a marketing data set including historical crossing feature values and marketing result values of potential truck customers in the previous marketing time period, the information gain of various historical crossing features to the marketing results is calculated to measure the contribution ratio of various historical crossing features to the marketing results, thereby adjusting the weights of various quantized values of crossing historical data when solving the potential truck customer information in the current marketing time period using the potential truck customer information determination model; and realizing adaptive parameter tuning of the weights of various quantized values of crossing historical data in the potential truck customer information determination model using the historical marketing success rate, thereby improving the accuracy of potential truck customer information determination, and thereby improving the success probability of marketing based on potential truck customer information. BRIEF DESCRIPTION OF THE DRAWINGS
[0013] In order to more clearly illustrate the technical solutions in the present application or related technologies, the following is a brief introduction to the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0014] Figure 1 It is a flowchart of an adaptive optimization method for determining potential truck customer information based on information entropy provided in an embodiment of the present application; Figure 2 It is a structural schematic diagram of a device for determining an adaptive optimization of potential truck customer information based on information entropy provided in an embodiment of the present application; Figure 3 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0015] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0016] Figure 1 is a flow chart of an adaptive optimization method for determining potential truck customer information based on information entropy provided in an embodiment of the present application, such as Figure 1 As shown, the method includes at least the following steps: S101, constructing a marketing data set of potential truck customers in a previous marketing time period, the marketing data set including historical sea crossing feature values obtained by statistically analyzing historical sea crossing data of potential truck customers in a historical time period close to the previous marketing time period, and marketing result values obtained by statistically analyzing actual sea crossing port data of potential truck customers in the previous marketing time period; S102, determining the information gain of various historical cross-sea features to the marketing results, and determining the contribution ratio of various historical cross-sea features to the marketing results based on the information gain; S103, adjusting the weights of the quantized values of various historical sea crossing data in the potential truck customer information determination model based on the contribution ratio, to obtain an optimized potential truck customer information determination model; S104. Determine the potential truck customer information within the current marketing period based on the optimized potential truck customer information determination model.
[0017] The adaptive optimization method for determining potential truck customer information based on information entropy provided in the embodiment of the present application constructs a marketing data set including historical crossing feature values and marketing result values of potential truck customers in the previous marketing time period, calculates the information gain of various historical crossing features to the marketing results, and measures the contribution ratio of various historical crossing features to the marketing results, thereby adjusting the weights of various types of quantized values of crossing historical data when solving the potential truck customer information in the current marketing time period using the potential truck customer information determination model; and realizes adaptive parameter tuning of the weights of various types of quantized values of crossing historical data in the potential truck customer information determination model using the historical marketing success rate, thereby improving the accuracy of potential truck customer information determination, and thereby improving the success probability of marketing based on potential truck customer information.
[0018] For S101, a marketing dataset of potential truck customers in the previous marketing period is constructed.
[0019] Specifically, the marketing data set includes historical sea crossing feature values obtained by statistically analyzing historical sea crossing data of potential truck customers in a historical time period close to a previous marketing time period, and marketing result values obtained by statistically analyzing actual sea crossing port data of potential truck customers in a previous marketing time period.
[0020] On the one hand, the actual sea port data of potential truck customers in the previous marketing period are counted to obtain the marketing result value. Specifically, there are two categories of marketing result values. If the potential truck customer actually chooses the target port to leave the island, it means that the marketing is successful, and the marketing result value RE is recorded as 1 or success; if the potential truck customer actually chooses other ports other than the target port to leave the island, it means that the marketing failed, and the marketing result value is recorded as 0 or failure. Alternatively, if the potential truck customer actually chooses the target port to leave the island, it means that the marketing is successful, and the marketing result value RE is recorded as 0 or success; if the potential truck customer actually chooses other ports other than the target port to leave the island, it means that the marketing failed, and the marketing result value is recorded as 1 or failure.
[0021] On the other hand, the historical sea crossing data of potential truck customers in the previous marketing period within the critical historical time period are counted to obtain the historical sea crossing characteristic value.
[0022] Specifically, during the off-season for passenger ferry business, trucks that have entered the island but have not yet left the island are the main targets for competition or marketing by various ports. Potential truck customers are truck customers who have not left the island in the historical time period before the marketing period. Since trucks generally enter and leave the island in a relatively short period of time, the selection of marketing time periods and nearby historical time periods also has a strong timeliness.
[0023] By assigning values to various types of historical sea crossing data of potential truck customers, the quantitative values of the historical sea crossing data are obtained, and then the quantitative values of various types of historical sea crossing data are weighted summed to obtain the potential truck customer information of the potential truck customers. The potential truck customer information is used to characterize the success probability of selecting the target port to leave the island after marketing to the potential truck customers.
[0024] The historical sea crossing characteristic values of potential truck customers are obtained by statistically analyzing the historical sea crossing data. Specifically, in the process of determining the potential truck customer information in the previous marketing period, various types of historical sea crossing data are assigned values to obtain the quantitative values of the corresponding data. Then, in the adaptive optimization process of determining the potential truck customer information, the historical sea crossing data can be used as the historical sea crossing characteristic values; optionally, the quantitative values obtained after the historical sea crossing data are assigned values can be used as the historical sea crossing characteristic values. The categories of the historical sea crossing characteristic values correspond to the categories of the historical sea crossing data.
[0025] In some embodiments, historical sea crossing data can be classified into sea crossing frequency data TF, sea crossing port selection data HC, frequently transported cargo data SP and market volatility factor MS, etc. By introducing the influencing factor: market volatility factor, the market volatility can be more comprehensively reflected, and the marketing accuracy and success rate can be improved.
[0026] Among them, the sea crossing frequency data is used to describe the sea crossing frequency of potential truck customers in the historical period; the sea crossing port selection data is used to describe the port selection of potential truck customers when crossing the sea in the historical period; the commonly transported cargo data is used to describe the cargo types transported by sea crossing trucks when crossing the sea during the historical event period; the market volatility factor is used to describe the temporal fluctuations of passenger and vehicle ferry freight tasks.
[0027] The process of determining the potential truck customer information of the potential truck customer can be described by a potential customer information determination model. Optionally, the potential customer information determination model satisfies:
[0028] Among them, TCM represents the potential truck customer information, TFP, HCP, SPP and MSP represent the quantitative values of sea crossing frequency, sea crossing port selection, frequently transported cargo types and market volatility factor, respectively. , , and They respectively represent the weights of various historical quantitative values.
[0029] Correspondingly, historical sea crossing characteristics can be classified into sea crossing frequency characteristics, sea crossing port selection characteristics, frequently transported cargo characteristics and market fluctuation characteristics.
[0030] The following is an example of the process of assigning values to various types of historical sea crossing data to obtain the quantitative values of the corresponding data in the process of determining potential truck customer information in the previous marketing period.
[0031] For example, the sea crossing frequency data TF is assigned a value as follows: If the frequency of crossing the sea by a potential truck customer is ≥ 20 times, the frequency data TF is high, and the frequency quantification value TFP is assigned a value of 3; If 10 times ≤ the number of times potential truck customers cross the sea < 20 times, the crossing frequency data TF is medium, and the crossing frequency quantization value TFP is assigned a value of 2; If the frequency of crossing the sea by a potential truck customer is less than 20 times, the frequency data TF is low, and the quantified value TFP is assigned a value of 1.
[0032] For example, the assignment process of the sea port selection data HC is as follows: If the proportion of sea crossing selected by potential truck customers at the target port is ≥ 60%, the sea crossing port selection data HC is loyal, and the sea crossing port selection quantification value HCP is assigned a value of 3; If 40%≤the proportion of potential truck customers choosing the target port for sea crossing is <60%, then the sea crossing port selection data HC is swinging, and the sea crossing port selection quantification value HCP is assigned a value of 2; If the proportion of potential truck customers choosing the target port for sea crossing is less than 40%, the sea crossing port selection data HC is normal, and the sea crossing port selection quantification value HCP is assigned a value of 1.
[0033] For example, the frequently-pulled cargo data SP is assigned values as follows: If the goods that potential truck customers may carry are agricultural products, seafood, refrigerated goods, and other goods that require high timeliness in sea transportation, then the data of the commonly transported goods SP is urgent, and the quantitative value SPP of the commonly transported goods is assigned a value of 3; If the potential truck customers may carry goods such as wood, steel, express delivery and other goods with normal timeliness requirements for sea crossing, then the data of commonly transported goods SP is medium, and the quantitative value SPP of commonly transported goods is assigned a value of 2; If the potential truck customer may carry other goods that have lower requirements for sea crossing timeliness, the data SP of the commonly transported goods will be slow, and the quantified value SPP of the commonly transported goods will be assigned a value of 1.
[0034] For example, the market volatility factor MS is assigned a value as follows: If the market volatility factor MS is in the peak season, the market volatility quantification value MSP is assigned a value of 3; If the market volatility factor MS is normal, the market volatility quantitative value MSP is assigned a value of 2; If the market volatility factor MS is in the off-season, the market volatility quantification value MSP is assigned a value of 1.
[0035] It should be noted that the above is only an example of assigning values to various types of historical sea crossing data, and the assignment method for various types of historical sea crossing data is not limited in the embodiments of the present application.
[0036] A marketing data set of potential truck customers in the previous marketing period is constructed through historical sea crossing feature values and marketing result values of potential truck customers in the previous marketing period. The marketing data set can be displayed in a table form.
[0037] If the historical crossing data is used as the historical crossing feature value, the marketing data set is constructed as shown in Table 1.
[0038] Table 1: Marketing dataset example 1
[0039] If the quantitative value of historical sea crossing data is used as the historical sea crossing feature value, the marketing data set is constructed as shown in Table 2.
[0040] Table 2: Marketing dataset example 2
[0041] For S102, the information gain of each type of historical cross-sea features to the marketing results is determined, and the contribution ratio of each type of historical cross-sea features to the marketing results is determined based on the information gain.
[0042] Specifically, information entropy is an indicator to measure the uncertainty of random variables. In the embodiment of the present application, information entropy is used to achieve adaptive optimization of potential truck customer information determination, calculate the information gain of various historical crossing characteristics to the marketing data set, and further calculate the contribution ratio of various historical crossing characteristics, thereby achieving adaptive optimization of the weights of various historical crossing data quantization values in the process of determining potential truck customer information.
[0043] In some embodiments, determining the information gain of various historical cross-border features on marketing results in S102 specifically includes: Determine empirical entropy of marketing results; Determine the empirical conditional entropy of various historical crossing characteristics on marketing results; Based on empirical entropy and empirical conditional entropy, the information gain of various historical cross-sea features on marketing results is determined.
[0044] Specifically, empirical entropy is used to measure the uncertainty or confusion of a random variable. The probability distribution of the discrete random variable "marketing results" satisfy:
[0045] in, is the probability of the i-th marketing result value, represents the number of samples of the i-th marketing result value in the marketing data set, Represents the total number of samples of marketing result values in the marketing data set. There are only two types of marketing result values: success and failure, or 1 and 0. Then determine the empirical entropy of the marketing result ,satisfy:
[0046] Furthermore, the empirical conditional entropy refers to the empirical conditional entropy under a certain condition constraint, which determines the empirical conditional entropy of various historical cross-sea characteristics on marketing results, specifically satisfying:
[0047] in, represents the empirical conditional entropy of the j-th historical cross-sea feature on marketing results, represents the number of samples of the i-th marketing result value in the marketing data set, Represents the total number of samples of marketing result values in the marketing dataset, It represents the number of samples with the kth value in the jth type of historical crossing-sea characteristic value, and K represents the number of values of the jth type of historical crossing-sea characteristic value.
[0048] For example, taking the aforementioned frequency data of crossing the sea as the frequency feature of crossing the sea, the empirical conditional entropy of the frequency feature of crossing the sea on the marketing results satisfies:
[0049] Among them, there are three possible values for the crossing frequency characteristic value: high, medium and low, or 3, 2 and 1.
[0050] Furthermore, the information gain of a certain type of historical features on marketing results indicates the degree to which the uncertainty of the marketing result category is reduced by knowing the value of the historical features. The information gain of various historical features on marketing results is calculated by using the empirical entropy of the marketing results and the empirical conditional entropy of various historical features on marketing results, which specifically meets the following requirements:
[0051] in, Represents the information gain of the j-th historical feature on the marketing results.
[0052] In some embodiments, determining the contribution ratio of each type of historical sea crossing feature based on information gain in S102 includes: The information gain of various historical cross-sea features on marketing results is normalized to determine the contribution ratio of various historical cross-sea features to marketing results.
[0053] Specifically, the information gain of various historical sea-crossing characteristics on marketing results will eventually be reflected in the weights of the quantitative values of various historical sea-crossing data in the potential truck customer information determination model. Therefore, it is necessary to normalize the information gain of various historical sea-crossing characteristics on marketing results and determine the contribution ratio of various historical sea-crossing characteristics to marketing results.
[0054] Optionally, the normalization method is specifically: First, the information gain of various historical crossing features Perform the summation process to obtain the total information gain gA, which satisfies: gA=
[0055] Among them, J is the number of categories of historical sea crossing characteristics, for example, J=4, which are sea crossing frequency characteristics, sea crossing port selection characteristics, frequently transported cargo characteristics and market fluctuation characteristics.
[0056] Secondly, the information gain of various historical crossing features Divide by gA to get the contribution ratio of different categories of historical cross-border features to the marketing results, and complete the normalization process.
[0057] For S103, adjust the weights of various types of historical cross-sea data quantization values in the potential truck customer information determination model based on the contribution ratio to obtain the optimized potential truck customer information determination model; S104, determine the potential truck customer information in the current marketing time period based on the optimized potential truck customer information determination model.
[0058] After completing the statistical analysis of the contribution ratios of various historical cross-sea characteristics to the marketing results in the previous marketing time period, the weights of the quantitative values of various historical cross-sea data in the potential truck customer information determination model are adjusted to achieve adaptive optimization of the potential truck customer information determination model; thereby, the optimized potential truck customer information determination model is used to calculate the potential truck customer information in the current marketing time period, and marketing is then carried out based on the calculated potential truck customer information.
[0059] The following is a description of the adaptive optimization device for determining potential truck customer information based on information entropy provided in the present application. The adaptive optimization device for determining potential truck customer information based on information entropy described below and the adaptive optimization method for determining potential truck customer information based on information entropy described above can refer to each other.
[0060] Figure 2 is a schematic diagram of the structure of the adaptive optimization device for determining potential truck customer information based on information entropy provided in an embodiment of the present application, such as Figure 2 As shown, the device at least includes: A construction module 201 is used to construct a marketing data set of potential truck customers in a previous marketing time period, wherein the marketing data set includes a historical sea crossing feature value obtained by statistically analyzing the historical sea crossing data of potential truck customers in a historical time period close to the previous marketing time period, and a marketing result value obtained by statistically analyzing the actual sea crossing port data of potential truck customers in the previous marketing time period; The first determination module 202 is used to determine the information gain of various historical cross-sea features to the marketing results, and determine the contribution ratio of various historical cross-sea features to the marketing results based on the information gain; An optimization module 203 is used to adjust the weights of the quantized values of various historical sea crossing data in the potential truck customer information determination model based on the contribution ratio to obtain an optimized potential truck customer information determination model; The second determination module 204 is used to determine the potential truck customer information within the current marketing period based on the optimized potential truck customer information determination model.
[0061] In some embodiments, determining the information gain of various historical features on the marketing dataset includes: Determine empirical entropy of marketing results; Determine the empirical conditional entropy of various historical crossing characteristics on marketing results; Based on empirical entropy and empirical conditional entropy, the information gain of various historical cross-sea features on marketing results is determined.
[0062] In some embodiments, the empirical entropy of a marketing result is determined such that:
[0063] in, represents the empirical entropy of marketing results, Represents the probability of the i-th marketing result value.
[0064] In some embodiments, the empirical conditional entropy of various historical cross-border features on marketing results is determined to satisfy:
[0065] in, represents the empirical conditional entropy of the j-th historical cross-sea feature on marketing results, represents the number of samples of the i-th marketing result value in the marketing data set, Represents the total number of samples of marketing result values in the marketing dataset, It represents the number of samples with the kth value in the jth type of historical crossing-sea characteristic value, and K represents the number of values of the jth type of historical crossing-sea characteristic value.
[0066] In some embodiments, the information gain of various historical cross-border features on marketing results is determined to satisfy:
[0067] in, Represents the information gain of the j-th historical feature on the marketing results.
[0068] In some embodiments, the contribution ratio of each type of historical sea crossing feature is determined based on information gain, including: The information gain of various historical cross-sea features on marketing results is normalized to determine the contribution ratio of various historical cross-sea features to marketing results.
[0069] In some embodiments, historical sea crossing characteristics are classified into: sea crossing frequency characteristics, sea crossing port selection characteristics, frequently transported cargo characteristics and market fluctuation characteristics.
[0070] In some embodiments, the potential truck customer information determination model satisfies:
[0071] Among them, TCM represents the potential truck customer information, TFP, HCP, SPP and MSP represent the quantitative values of sea crossing frequency, sea crossing port selection, frequently transported cargo types and market volatility factor, respectively. , , and They respectively represent the weights of various historical quantitative values.
[0072] It can be understood that the detailed functional implementation of each of the above-mentioned units / modules can be found in the introduction of the aforementioned method embodiment, and will not be repeated here.
[0073] It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment. The implementation principle and technical effect of the corresponding program module in the device are similar to those described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method, which will not be repeated here.
[0074] Based on the method in the above embodiment, an embodiment of the present application provides an electronic device. The device may include: at least one memory for storing programs and at least one processor for executing the programs stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method described in the above embodiment.
[0075] Figure 3 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 3 As shown, the electronic device may include: a processor (Processor) 301, a communication interface (Communications Interface) 302, a memory (Memory) 303 and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other through the communication bus 304. The processor 301 can call the software instructions in the memory 303 to execute the method described in the above embodiment.
[0076] In addition, the logic instructions in the above-mentioned memory 303 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.
[0077] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method in the above embodiment.
[0078] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment.
[0079] It is understandable that the processor in the embodiment of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.
[0080] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.
[0081] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.
[0082] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.
[0083] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.
Claims
1. An adaptive optimization method for determining potential truck customer information based on information entropy, characterized in that: include: Constructing a marketing data set of potential truck customers in a previous marketing time period, the marketing data set including historical sea crossing feature values obtained by statistically analyzing historical sea crossing data of the potential truck customers in a historical time period close to the previous marketing time period, and marketing result values obtained by statistically analyzing actual sea crossing port data of the potential truck customers in the marketing time period; Determine the information gain of various historical cross-sea features to the marketing results, and determine the contribution ratio of various historical cross-sea features to the marketing results based on the information gain; Based on the contribution ratio, the weights of the quantized values of various historical sea crossing data in the potential truck customer information determination model are adjusted to obtain an optimized potential truck customer information determination model; The potential truck customer information within the current marketing time period is determined based on the optimized potential truck customer information determination model.
2. The method for determining potential truck customer information according to claim 1 is characterized in that: The determining of the information gain of various historical cross-sea features on the marketing data set includes: determining the empirical entropy of said marketing results; Determine the empirical conditional entropy of various historical crossing characteristics on the marketing results; Based on the empirical entropy and the empirical conditional entropy, the information gain of various historical cross-sea features on the marketing result is determined.
3. The method for determining potential truck customer information according to claim 2 is characterized in that: The empirical entropy of determining the marketing result satisfies: in, represents the empirical entropy of the marketing result, Represents the probability of the i-th marketing result value.
4. The method for determining potential truck customer information according to claim 3 is characterized in that: The determination of the empirical conditional entropy of various historical cross-sea features on the marketing results satisfies: in, represents the empirical conditional entropy of the j-th historical cross-sea feature on marketing results, represents the number of samples of the i-th marketing result value in the marketing data set, represents the total number of samples of marketing result values in the marketing dataset, It represents the number of samples with the kth value in the jth type of historical crossing-sea characteristic value, and K represents the number of values of the jth type of historical crossing-sea characteristic value.
5. The method for determining potential truck customer information according to claim 4 is characterized in that: The information gain of various historical cross-sea features on the marketing results is determined to meet the following requirements: in, Represents the information gain of the j-th historical feature on the marketing results.
6. The method for determining potential truck customer information according to claim 1 is characterized in that: The determining of the contribution ratio of various historical sea crossing features based on the information gain includes: The information gain of various historical cross-sea features to the marketing results is normalized to determine the contribution ratio of various historical cross-sea features to the marketing results.
7. The method for determining potential truck customer information according to any one of claims 1 to 6, characterized in that: The historical sea crossing characteristics are classified into: sea crossing frequency characteristics, sea crossing port selection characteristics, frequently transported cargo characteristics and market fluctuation characteristics.
8. The method for determining potential truck customer information according to claim 7 is characterized in that: The potential truck customer information determination model satisfies: Among them, TCM represents the potential truck customer information, TFP, HCP, SPP and MSP represent the quantitative values of sea crossing frequency, sea crossing port selection, frequently transported cargo types and market volatility factor, respectively. , , and They respectively represent the weights of various historical quantitative values.
9. An adaptive optimization device for determining potential truck customer information based on information entropy, characterized in that: include: A construction module is used to construct a marketing data set of potential truck customers in a previous marketing time period, wherein the marketing data set includes a historical sea crossing feature value obtained by statistically analyzing historical sea crossing data of the potential truck customers in a historical time period close to the previous marketing time period, and a marketing result value obtained by statistically analyzing actual sea crossing port data of the potential truck customers in the marketing time period; The first determination module is used to determine the information gain of various historical cross-sea features to the marketing results, and determine the contribution ratio of various historical cross-sea features to the marketing results based on the information gain; An optimization module, used for adjusting the weights of the quantized values of various historical sea crossing data in the potential truck customer information determination model based on the contribution ratio, to obtain an optimized potential truck customer information determination model; The second determination module is used to determine the potential truck customer information within the current marketing time period based on the optimized potential truck customer information determination model.
10. An electronic device, characterized in that: include: at least one memory for storing a computer program; At least one processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method according to any one of claims 1 to 8.