Order prediction method and device for personalized customization

Abstract

The invention provides an order prediction method and device for personalized customization, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining a demand state value of a customer i at a moment t, demands of customers in historical data, and uncertain factors following historical selection; through customer personalized customization demand self-organization clustering of an HK model, determining the demand of the customer i at the t + 1 moment by using the demand state value of the customer i at the t moment, the demands of the customers in the historical data and the uncertain factors following the historical selection; and generating an order prediction result of the customer i at the t + 1 moment according to the demand of the customer i at the t + 1 moment, and outputting the order prediction result. According to the embodiment of the invention, when personalized customized order prediction is carried out, customer information exchange data is combined, and the influence of information exchange between customers on order data is considered.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and device for predicting orders for personalized customization. Background Art

[0002] In an era where intelligent manufacturing is the core goal, using big data, the Internet, and machine learning to empower the production management of enterprises, accurately predict customer order demands, and plan production and operation activities accordingly can not only significantly improve the level of intelligent production management of enterprises, but also help improve the core competitiveness of enterprises. As the source of supply chain management, the accuracy of order forecasting will directly affect the efficient operation, cost advantage, and delivery satisfaction of enterprises. Li Chao (Li Chao: Research and Application of Order Cost Forecasting and Order Monitoring in Building Materials Equipment Industry [J]. Machinery Manufacturing, 2016, 54(3): 84-86) studied and discussed the order cost forecasting and order monitoring issues in the building materials equipment industry, proposed to integrate the order cost information through the ERP system, establish an order cost instance library, add an expert system module, and predict the order cost through the BP neural network model. Xue Bing et al. (Xue Bing, Ma Weidong. Research on building materials equipment order prediction based on ARMA model [J]. Mechanical Engineer, 2014, 272 (2): 130-132) studied the building materials equipment order prediction method based on ARMA model, and proposed to use time series theory to establish a model to analyze the order volume of equipment manufacturing enterprises. Wang Changqiong et al. (Wang Changqiong, Cao Mieqing, Wang Yanli, Qiu Jie, Liu Xiaoyu. Research on combined prediction of e-commerce order volume based on fusion Baidu index [J]. Computer Engineering and Applications, 2018, 54 (12): 219-225) In order to improve the prediction accuracy of order volume, a combined prediction model based on fusion network search index is proposed by combining the prediction advantages of BP neural network, BP neural network based on Adaboost and support vector machine, and an indicator system integrating Baidu index and e-commerce user order information is constructed.

[0003] The above research explored different algorithms for the problem of intelligent order prediction in production. Among them, algorithms such as statistical methods and machine learning-based methods can successfully solve the problem and achieve goals such as order cost prediction and order quantity monitoring.

[0004] However, these algorithms mostly make predictions based on historical order data, without considering the impact of information exchange between customers on order data under the conditions of the contemporary industrial Internet. Summary of the invention

[0005] In order to solve the technical problem that order data prediction in the prior art does not consider the impact of information exchange between customers on order data, the embodiment of the present invention provides a method and device for personalized order prediction. The technical solution is as follows:

[0006] In one aspect, a method for order prediction for personalized customization is provided, the method comprising:

[0007] Get the demand state value of customer i at time t, the customer's demand in historical data, and the uncertain factors of historical selection;

[0008] By self-organizing clustering of customer personalized customization needs based on the HK model, the needs of customer i at time t, the needs of customers in the historical data, and the uncertain factors following the historical selection are used to determine the needs of customer i at time t+1;

[0009] According to the demand of customer i at time t+1, an order prediction result of customer i at time t+1 is generated, and the order prediction result is output.

[0010] Optionally, the self-organizing clustering of customer personalized customization needs through the HK model uses the demand state value of customer i at time t, the customer needs in the historical data, and the uncertain factors following the historical selection to determine the needs of customer i at time t+1, which is performed by the following formula:

[0011] Among them, x i (t+1) is the demand of customer i at time t+1, x i represents the demand state value of customer i at time t, c represents the customer's demand in historical data, σ represents the uncertain factors following historical selection, N i (x i )={j∈V:|x i -x j (t)|≤ε1},I i (x i )={j∈V:|x i -x j (t)|≤ε2},α i ∈(0,1] is the size of the customer's order area, I {i∈S} is the indicator function, which takes the value 1 or 0 according to whether i∈S or not, S is the set of neighbors for individual information interaction, N i (x(t)),I i (x(t)) are customer demands x at different thresholds at time t i(t) The corresponding neighbor set, where |·| can be the cardinality of the neighbor set or the absolute value of a real number, ε1∈(0,1] represents the confidence threshold of one neighbor set, ε2∈(0,1] represents the confidence threshold of two neighbor sets, β i is the sensitivity to market factors, β i ∈[0,1],γ i is the impact of the emergency, V = {1, 2, ..., n} is the set of n customer personalized customization requirements, x i ∈[0,1], i∈V.

[0012] Optionally, the γ i When no emergency occurs, the value is 0. i The value is 1 when an emergency occurs.

[0013] Optionally, the ε1 is 0.1, and the ε2 is 0.05.

[0014] Optionally, the β i It can be divided into three levels: very sensitive, moderately sensitive and not very sensitive.

[0015] Optionally, a very sensitive level corresponding to β i The value is 0.8, and the β corresponding to the general sensitivity level i The value is 0.5, which is not very sensitive. i The value is 0.2.

[0016] Optionally, the α i The value of is 0.2, 0.5 or 0.8.

[0017] On the other hand, an order prediction device for personalized customization is provided, and the order prediction device for personalized customization is used to implement the order prediction method for personalized customization provided by the present invention, and the device includes:

[0018] The acquisition module is used to obtain the demand state value of customer i at time t, the customer's demand in historical data, and the uncertain factors following historical selection;

[0019] A determination module, for determining the demand of customer i at time t+1 by self-organizing clustering of customer personalized customization demand of HK model, using the demand state value of customer i at time t, the demand of customer in the historical data, and the uncertain factors following the historical selection;

[0020] The output module is used to generate an order prediction result of the customer i at time t+1 according to the demand of the customer i at time t+1, and output the order prediction result.

[0021] On the other hand, an order prediction device for personalized customization is provided, and the order prediction device for personalized customization includes:

[0022] processor;

[0023] A memory having computer-readable instructions stored therein, wherein the method provided by the present invention is implemented when the computer-readable instructions are executed by the processor.

[0024] On the other hand, a computer-readable storage medium is provided, in which a program code is stored. The program code can be called by a processor to execute the method provided by the present invention.

[0025] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0026] The embodiment of the present invention uses the self-organizing clustering of customer personalized customization needs of the HK model, and uses the demand state value of customer i at time t, the customer needs in the historical data, and the uncertain factors that follow the historical selection to determine the needs of customer i at time t+1. Since the HK model is a viewpoint dynamics model, it originally considers the identity of individual views in bounded information exchange, and the individual fuzzy demand model further considers the diversity and variability of individual needs, making the evolution process of the HK model more realistic. Therefore, when predicting personalized orders, customer information exchange data is combined, and the impact of information exchange between customers on order data is considered. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 This is a flow chart of an order prediction method for personalized customization provided by an embodiment of the present invention;

[0029] Figure 2 is a simulation prediction result provided by an embodiment of the present invention;

[0030] Figure 3 is another simulation prediction result provided by an embodiment of the present invention;

[0031] Figure 4 This is a block diagram of an order prediction device for personalized customization provided by an embodiment of the present invention;

[0032] Figure 5It is a structural schematic diagram of an order prediction device for personalized customization provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0034] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0035] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0036] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are consistent.

[0037] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0038] In order to solve the technical problem that order data prediction in the prior art does not consider the impact of information exchange between customers on order data, the embodiment of the present invention provides a method and device for personalized order prediction. The technical solution is as follows:

[0039] On the one hand, if Figure 1 As shown, a method for order prediction for personalized customization is provided, the method comprising:

[0040] S1, obtain the demand state value of customer i at time t, the customer's demand in historical data, and the uncertain factors of historical selection;

[0041] S2. Self-organizing clustering of customer personalized customization needs based on the HK model, using the demand state value of customer i at time t, the customer needs in the historical data, and the uncertain factors following the historical selection, to determine the needs of customer i at time t+1;

[0042] S3. Generate an order prediction result of the customer i at time t+1 according to the demand of the customer i at time t+1, and output the order prediction result.

[0043] Optionally, the self-organizing clustering of customer personalized customization needs through the HK model uses the demand state value of customer i at time t, the customer needs in the historical data, and the uncertain factors following the historical selection to determine the needs of customer i at time t+1, which is performed by the following formula:

[0044] Among them, x i (t+1) is the demand of customer i at time t+1, x i represents the demand state value of customer i at time t, c represents the customer's demand in historical data, σ represents the uncertain factors following historical selection, N i (x i )={j∈V:|x i -x j (t)|≤ε1},I i (x i )={j∈V:|x i -x j (t)|≤ε2},α i ∈(0,1] is the size of the customer's order area, I {i∈s} is the indicator function, which takes the value 1 or 0 according to whether i∈S or not, S is the set of neighbors for individual information interaction, N i (x(t)),I i (x(t)) are customer demands x at different thresholds at time t i (t) The corresponding neighbor set, where |·| can be the cardinality of the neighbor set or the absolute value of a real number, ε1∈(0,1] represents the confidence threshold of one neighbor set, ε2∈(0,1] represents the confidence threshold of two neighbor sets, β i is the sensitivity to market factors, β i ∈[0,1],γ i is the impact of the emergency, V = {1, 2, ..., n} is the set of n customer personalized customization requirements, x i ∈[0,1], i∈V.

[0045] Optionally, the γ i When no emergency occurs, the value is 0. i The value is 1 when an emergency occurs.

[0046] Optionally, the ε1 is 0.1, and the ε2 is 0.05.

[0047] Optionally, the βi It can be divided into three levels: very sensitive, moderately sensitive and not very sensitive.

[0048] Optionally, a very sensitive level corresponding to β i The value is 0.8, and the β corresponding to the general sensitivity level i The value is 0.5, which is not very sensitive. i The value is 0.2.

[0049] Optionally, the α i The value of is 0.2, 0.5 or 0.8.

[0050] In order to solve the technical problem that order data prediction in the prior art does not take into account the impact of information exchange between customers on order data, the present invention provides an order prediction method for personalized customization. By clustering analysis of historical customer ordering behaviors, the order demand for the next stage is predicted, and customer demand preferences are fuzzy processed, which is more in line with the characteristics of the Industrial Internet.

[0051] First, the HK model of customer personalized customization needs is applied to self-organize and cluster customer needs; secondly, customer demand preferences are fuzzified; finally, the fuzzified customer demand preferences are brought into the HK model for order forecasting. The forecast results are transmitted to the enterprise manufacturer for big data storage and analysis, and resource allocation and production scheduling are carried out on the intelligent production line according to the forecast results, while the production process of the product is monitored in the cloud. The whole process simulates the collective collaborative wisdom based on local information interaction in nature and society, and the enterprise order forecast model and customer personalized customization needs are assimilated, adapted, and collaboratively decided. Ultimately, the enterprise achieves low-cost, high-efficiency, and all-round "small batch, multiple batch" production and manufacturing to meet the diverse, fragmented, and personalized consumer needs of customers.

[0052] The order prediction method for personalized customization provided by the present invention is inferred in the following way:

[0053] A) Design a bearing steel order forecasting process;

[0054] B) Propose a self-organizing clustering method for customer personalized customization needs based on the HK model;

[0055] C) proposes an individual fuzzy demand model, combined with step B) to achieve the goal of dynamically combining enterprise order forecasting with customer personalized customization needs.

[0056] Furthermore, in the step A), first, the customer personalized customization demand HK model is applied to self-organize clustering of customer ordering behavior; secondly, the clustering result is brought into the individual fuzzy demand model; finally, the prediction result is transmitted to the enterprise manufacturer, and resource allocation and production scheduling are performed on the intelligent production line according to the prediction result.

[0057] Furthermore, the self-organizing clustering method for customer personalized customization demand based on HK model in step B) is implemented in the following way:

[0058] With the continuous improvement of steel mills' production processes and the emergence of new steel products, the demand and types of steel in sales orders have become flexible and diverse, especially bearing steel. The pursuit of mass-produced common products has been unable to meet customers' personalized and fragmented needs.

[0059] Customers' demand for personalized customization involves the dynamic changes in their ordering behavior, which inevitably requires a process of understanding the evolution of large-scale customer ordering behavior. Therefore, it is necessary to establish an effective method based on local rules.

[0060] It simulates the collective intelligence based on local information interaction in nature and society. Based on the traditional HK model of viewpoint dynamics, it considers the customer order area, the influence of market factors and the impact of major emergencies to reveal the essence and inherent laws hidden in the surface phenomena.

[0061] Let V = {1, 2, ..., n} be the set of n customers’ personalized customization requirements, x i (t) represents customer demand; x i (t)∈[0,1], i∈V, t≥0, represents time t. Based on the local interaction rules, the self-organizing clustering rules of customer personalized customization demand based on HK model are designed:

[0062] in,

[0063]

[0064] N i (x(t))={j∈V:|Ax j (t)|≤ε1},

[0065] I i (x(t))={j∈V:|Ax j (t)|≤ε2},

[0066]

[0067] Where: α i ∈(0,1] is the size of the customer's order area; I {i∈s} is the indicator function, which takes the value 1 or 0 according to whether i∈S or not; N i (x(t)),I i(x(t)) are the neighbor sets corresponding to customer demand under different thresholds at time t, where |·| can be the cardinality of the neighbor set or the absolute value of a real number; ε1∈(0,1] represents the confidence threshold of a neighbor set, and ε2∈(0,1] represents the confidence threshold of two neighbor sets; f is the degree of influence of market factors and emergencies on customer demand; β i is the sensitivity to market factors, β i ∈[0,1]; γ i The impact of the emergency.

[0068] Furthermore, the step C) is achieved by:

[0069] Human opinions are inherently ambiguous (uncertain), so an opinion and its uncertainty are two sides of the same coin and should be considered simultaneously when we study the formation and evolution of opinions.

[0070] Many of the opinions of customers are acquired through social learning, that is, through communication with other people in society. Similarly, many of the needs of customers are also obtained from market communication. The demand preferences are expressed as fuzzy sets, and the fuzzy sets are used as opinion individuals in the HK model. The HK model of fuzzy sets is called the fuzzy opinion HK model.

[0071] The main differences between fuzzy opinion theory and traditional theory are: first, traditional theory is a simple individual with a single content, while the characteristics of individual opinions in fuzzy opinion theory are the central idea (the center of the Gaussian fuzzy set) and the uncertainty of these ideas (the standard deviation of the Gaussian fuzzy set). The opinions expressed by people in communication are mainly based on fuzzy words and fuzzy expressions, so using a single point with clear content to represent a person oversimplifies the situation and makes it difficult to analyze some key issues in human interaction within the framework of the traditional HK model.

[0072] Therefore, the individual x in the personalized customer demand preference prediction model is fuzzy processed:

[0073]

[0074] x i (t) represents the preference of the xth customer demand. Specifically, x i (t) represents the demand state value of customer i at time t, c represents the customer's demand in historical data, and σ represents the uncertain factors following historical choices.

[0075] Substituting into formula (1) we get:

[0076]

[0077] In the simulation experiment, the industrial Internet complex system is used as the application scenario. For step C), the production management system for bearing steel enterprises facing the multi-variety small batch order mode is used. The historical order data is cleaned and pre-processed, and the order area (the order area is equal to the product of the preferred order amount and the order demand quantity under the preferred category) parameter is brought into the model.

[0078] Set ε1 to 0.1 and ε2 to 0.05. The initial value of user demand is randomly generated in [0,1]. For model (6), set c to 0 and the standard deviation σ to 0.5. Sensitivity β i It can be divided into three levels: very sensitive, moderately sensitive, and not very sensitive, with values ​​of 0.8, 0.5, and 0.2 respectively. i The values ​​of are set to 0.2, 0.5, and 0.8 respectively. Use the following two examples for simulation.

[0079] Example 1. Assume that the customer demand quantity is 20. Figure 2 As shown, the final prediction results of customer demand preference are two groups, namely J1=0.3614 and J2=0.1793.

[0080] Example 2. The number of customer demands is 100. Through simulation, it can be intuitively seen that the final prediction results of customer demand preferences are four groups, such as Figure 3 The corresponding preference prediction values ​​are J1=0.3708, J2=0.3444, J3=0.1826 and J4=0.0737.

[0081] The prediction results of personalized customization demand preference are as follows: Figure 2 and Figure 3 shown.

[0082] On the other hand, Figure 4 As shown, an order prediction device for personalized customization is provided, and the order prediction device for personalized customization is used to implement the order prediction method for personalized customization provided by the present invention, and the device includes:

[0083] Acquisition module 401, used to obtain the demand state value of customer i at time t, the customer's demand in historical data, and the uncertain factors following historical selection;

[0084] Determination module 402, for determining the demand of customer i at time t+1 by self-organizing clustering of customer personalized customization demand of HK model, using the demand state value of customer i at time t, the demand of customer in the historical data, and the uncertain factors following the historical selection;

[0085] The output module 403 is used to generate an order prediction result of the customer i at time t+1 according to the demand of the customer i at time t+1, and output the order prediction result.

[0086] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0087] The embodiment of the present invention uses the self-organizing clustering of customer personalized customization needs of the HK model, and uses the demand state value of customer i at time t, the customer needs in the historical data, and the uncertain factors that follow the historical selection to determine the needs of customer i at time t+1. Since the HK model is a viewpoint dynamics model, it originally considers the identity of individual views in bounded information exchange, and the individual fuzzy demand model further considers the diversity and variability of individual needs, making the evolution process of the HK model more realistic. Therefore, when predicting personalized orders, customer information exchange data is combined, and the impact of information exchange between customers on order data is considered.

[0088] Figure 5 is a structural diagram of a device for personalized order prediction provided by an embodiment of the present invention, such as Figure 5 As shown, optionally, the order prediction device 510 for personalized customization may include a first processor 2001.

[0089] Optionally, the order prediction device 510 for personalized customization may further include a memory 2002 and a transceiver 2003 .

[0090] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0091] Combine the following Figure 5 The components of the order prediction device 510 for personalized customization are specifically introduced as follows:

[0092] The first processor 2001 is a control center of the personalized order prediction device 510, which can be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (FPGAs).

[0093] Optionally, the first processor 2001 can perform various functions of the order prediction device 510 for personalized customization by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002.

[0094] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 5 CPU0 and CPU1 are shown in FIG.

[0095] In a specific implementation, as an embodiment, the order prediction device 510 for personalized customization may also include multiple processors, such as Figure 5 The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors can be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here can refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0096] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0097] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently, and may be connected to the first processor 2001 through the interface circuit ( Figure 5 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0098] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0099] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 5 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0100] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently, and communicate with the first processor 2001 through the interface circuit ( Figure 5 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0101] It should be noted that Figure 5 The structure of the order prediction device 510 for personalized customization shown in the figure does not constitute a limitation on the router. The actual knowledge structure recognition device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0102] In addition, the technical effects of the order prediction device 510 for personalized customization can refer to the technical effects of the order prediction method for personalized customization described in the above method embodiment, and will not be repeated here.

[0103] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0104] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0105] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments 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 or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by infrared, wireless, microwave or the like. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0106] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0107] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0108] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0109] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0110] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0111] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0112] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0113] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0114] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling 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 methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0115] 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. A method for order prediction for personalized customization, characterized in that: The method comprises: Get the demand state value of customer i at time t, the customer's demand in historical data, and the uncertain factors of historical selection; By self-organizing clustering of customer personalized customization needs based on the HK model, the needs of customer i at time t, the needs of customers in the historical data, and the uncertain factors following the historical selection are used to determine the needs of customer i at time t+1; According to the demand of customer i at time t+1, an order prediction result of customer i at time t+1 is generated, and the order prediction result is output.

2. The method according to claim 1, characterized in that The self-organizing clustering of customer personalized customization needs through the HK model uses the demand state value of customer i at time t, the customer needs in the historical data, and the uncertain factors following the historical selection to determine the needs of customer i at time t+1, which is performed through the following formula: Among them, x i (t+1) is the demand of customer i at time t+1, x i represents the demand state value of customer i at time t, c represents the customer's demand in historical data, σ represents the uncertain factors following historical selection, N i (x i )={j∈V:|x i -x j (t)|≤ε1},I i (x i )={j∈V:|x i -x j (t)|≤ε2},α i ∈(0,1] is the size of the customer's order area, I {i∈S} is the indicator function, which takes the value 1 or 0 according to whether i∈S or not, S is the set of neighbors for individual information interaction, N i (x(t)),I i (x(t)) are customer demands x at different thresholds at time t i (t) The corresponding neighbor set, where |·| can be the cardinality of the neighbor set or the absolute value of a real number, ε1∈(0,1] represents the confidence threshold of one neighbor set, ε2∈(0,1] represents the confidence threshold of two neighbor sets, β i is the sensitivity to market factors, β i ∈[0,1],γ i is the impact of the emergency, V = {1, 2, ..., n} is the set of n customer personalized customization requirements, x i ∈[0,1], i∈V.

3. The method according to claim 2, characterized in that The gamma i When no emergency occurs, the value is 0. i The value is 1 when an emergency occurs.

4. The method according to claim 2, characterized in that: The ε1 is 0.1, and the ε2 is 0.

05.

5. The method according to claim 2, characterized in that: The β i It can be divided into three levels: very sensitive, moderately sensitive and not very sensitive.

6. The method according to claim 5, characterized in that Beta corresponding to very sensitive level i The value is 0.8, and the β corresponding to the general sensitivity level i The value is 0.5, which is not very sensitive. i The value is 0.

2.

7. The method according to claim 2, characterized in that The α i The value of is 0.2, 0.5 or 0.

8.

8. An order prediction device for personalized customization, wherein the order prediction device for personalized customization is used to implement the order prediction method for personalized customization as described in any one of claims 1 to 7, characterized in that: The device comprises: The acquisition module is used to obtain the demand state value of customer i at time t, the customer's demand in historical data, and the uncertain factors following historical selection; A determination module, for determining the demand of customer i at time t+1 by self-organizing clustering of customer personalized customization demand of HK model, using the demand state value of customer i at time t, the demand of customer in the historical data, and the uncertain factors following the historical selection; The output module is used to generate an order prediction result of the customer i at time t+1 according to the demand of the customer i at time t+1, and output the order prediction result.

9. An order prediction device for personalized customization, characterized in that: The order prediction device for personalized customization includes: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 7.

Images