Model construction method and device for calculating and quantifying product industry sensitivity and contribution degree

Abstract

The invention relates to a model construction method for calculating the industry sensitivity and contribution degree of quantitative products, which comprises the following steps: determining n industries related to a quantitative product P, and selecting m representative quantitative products for each industry; segmenting the quantized product P and calculating the yield of each time slice Ti obtained by segmentation to obtain a yield sequence PP of t time slices and a yield matrix Pi, m, t of m products of any industry i in each time slice; setting a weight ratio of m products of any industry i, obtaining a weight sequence W, obtaining a yield rate sequence P'i of the fitting product Pi of any industry i in each time slice according to the yield rate matrix Pi, m, t and the weight sequence W, and thus obtaining a yield rate matrix N of the fitting product of any industry i in the time slice sequence T; and calculating according to the obtained yield rate sequence PP of the quantized product and the yield rate matrix N of the fitting product to obtain a sensitivity sequence W'and a contribution degree sequence Q of the quantized product P in n industries, thereby providing support for customers to select the quantized product.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a model building method, device, computer-readable storage medium, electronic device and program product for calculating the sensitivity and contribution of a quantitative product industry. Background Art

[0002] Traditional influencing factor analysis methods often rely on a single financial indicator or market trend, while today's industry impact analysis is increasingly inclined to multi-dimensional analysis. With the development of big data and computing technology, quantitative evaluation strategies have gradually become mainstream. Quantitative evaluation strategies use mathematical models to analyze and predict market behavior, striving to achieve objective and systematic investment decisions. Different investors have different risk preferences and return targets. The construction of quantitative calculation models can help investors customize investment strategies based on their personal investment attributes.

[0003] However, existing analytical strategies often use subjective and qualitative methods to determine the industry to which a quantitative product belongs, and are unable to measure the industry's impact on quantitative products and its contribution to the returns of quantitative products. Summary of the invention

[0004] In order to address the deficiencies of the prior art, the present invention constructs a model for calculating the industry sensitivity and contribution of quantitative products, so as to provide strong support for industry participants in judging the degree of influence of the industry on quantitative products and the degree of influence on the rate of return, i.e., the contribution.

[0005] To achieve the above objectives, the technical solutions adopted by the present invention include:

[0006] A method for constructing a model for calculating the sensitivity and contribution of a quantitative product industry, characterized by comprising:

[0007] S1. Determine the n industries involved in the quantitative product P, and select m representative quantitative products for each industry;

[0008] S2. Split the quantified product P into t intervals of pending revenue, and calculate each time slice T obtained by the splitting. i The yield of t time slices is obtained by P , the return matrix P of m products in any industry i in each time slice i,m,t ;

[0009] S3, set the weight proportion of m products in any industry i, obtain the weight sequence W, according to the yield matrix P i,m,t The product of the weight sequence W is obtained by multiplying the fitted product P of any industry i i In each time slice, the yield sequence P′ i, thus obtaining the yield matrix N of the fitting products of any industry i in the time slice sequence T;

[0010] S4. Calculate the sensitivity sequence and contribution sequence of the quantitative product P in n industries based on the yield sequence of the obtained quantitative product and the yield matrix N of the fitted product to provide support for customers to select quantitative products. Exemplarily, the S2 specifically includes: determining the overall time range [S, E] of the yield interval to be processed of the quantitative product, dividing the yield interval according to the preset length w and step length dt, where the first interval is: [S, S+w]; the kth interval is: [S+(k-1)*dt, S+(k-1)*dt+w], where: k≥2, S+(k-1)*dt+w≤E.

[0011] Exemplarily, obtaining the weight sequence W includes: combining the attributes of the quantitative products, using a linear regression model to train all products in any industry i, selecting m products that meet a set regression threshold, and assigning weights to the m products.

[0012] Exemplarily, the sensitivity calculation of any industry i includes: quantifying the product yield sequence:

[0013] The matrix of product yields for n industries:

[0014]

[0015] Substitute into the following regression equation:

[0016]

[0017] in, And, 0<w′ i <1, ε is the compensation residual value; through the regression equation calculation, the sensitivity w′ of the quantitative product P in industry i is obtained i .

[0018] Exemplarily, the step of obtaining the contribution sequence Q of the quantitative product P in n industries includes: obtaining the yield sequence N′ according to the fitted product yield matrix N; wherein the element p′ of N′ i is the mean of the elements in the N rows of the matrix, that is

[0019] Thus we get the yield sequence N′={p′1,p′2,…p′ i …p′ n};q i =w′ i *p′ i ;

[0020] Q={q1,q2,…qi …q n}={w′1*p′1, w′2*p′2,…w′ i *p′ i …w′ n *p′ n},

[0021] Among them, the element q in the contribution sequence Q i That is, the contribution of industry i to the yield of quantitative product P, q i The larger it is, the greater the contribution of industry i to the revenue of product P.

[0022] The present invention also provides a model building device for calculating the sensitivity and contribution of a quantitative product industry, which is characterized by comprising:

[0023] The representative quantitative product confirmation module is used to determine the n industries involved in the quantitative product P and select m representative quantitative products for each industry;

[0024] The yield calculation module is used to divide the pending yield intervals of the quantitative product P into t intervals and calculate each time slice T obtained by the segmentation. i The yield of t time slices is obtained by P , the return matrix P of m products in any industry i in each time slice i,m,t ;

[0025] The fitting product acquisition module is used to set the weight ratio of m products in any industry i, obtain the weight sequence W, and calculate the yield matrix P according to the yield matrix P. i,m,t The product of the weight sequence W is obtained by multiplying the fitted product P of any industry i i In each time slice, the yield sequence P′ i , thus obtaining the yield matrix N of the fitting products of any industry i in the time slice sequence T;

[0026] The sensitivity and contribution acquisition module calculates the sensitivity sequence and contribution sequence of the quantitative product P in n industries based on the obtained yield sequence of the quantitative product and the yield matrix N of the fitted product, providing support for customers to select quantitative products.

[0027] Exemplarily, the yield calculation module is also used to determine the overall time range [S, E] of the quantitative product's pending yield interval, according to the preset yield interval segmentation length w, step length dt, where the first interval is: [S, S+w]; the kth interval is: [S+(k-1)*dt, S+(k-1)*dt+w], where: k≥2, S+(k-1)*dt+w≤E.

[0028] The present invention also provides a computer-readable storage medium, characterized in that a computer program is stored on the storage medium, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

[0029] The present invention also provides an electronic device, characterized in that it includes a processor and a memory;

[0030] The memory is used to store computer programs;

[0031] The processor is configured to execute the method according to any one of claims 1 to 6 by calling a stored computer program.

[0032] The present invention also relates to a computer program product, comprising a computer program and / or instructions, characterized in that the computer program and / or instructions implement the steps of the above method when executed by a processor.

[0033] The beneficial effects of the present invention are as follows: the present invention provides strong support for industry participants in judging the degree of influence of the industry on the quantitative products and the degree of influence on the rate of return, i.e., the contribution, by constructing a model for calculating the industry sensitivity and contribution of quantitative products. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 The figure is a flow chart of the model building method for calculating the industry sensitivity and contribution of quantitative products according to the present invention.

[0035] Figure 2 A schematic diagram of the structure of the model for calculating the sensitivity and contribution of the quantitative product industry in the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0037] The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0038] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0039] The first aspect of the present invention relates to a model construction method for calculating the sensitivity and contribution of a quantitative product industry, such as Figure 1 As shown, including:

[0040] S1. Determine the n industries involved in the quantitative product P, and select m representative quantitative products for each industry;

[0041] S2. Split the quantified product P into t intervals of pending revenue, and calculate each time slice T obtained by the splitting. i The yield of t time slices is obtained by P , the return matrix P of m products in any industry i in each time slice i,m,t ;

[0042] S3, set the weight proportion of m products in any industry i, obtain the weight sequence W, according to the yield matrix P i,m,t The product of the weight sequence W is obtained by multiplying the fitted product P of any industry i i In each time slice, the yield sequence P′ i , thus obtaining the yield matrix N of the fitting products of any industry i in the time slice sequence T;

[0043] S4. Based on the obtained yield sequence of quantitative products and the yield matrix N of fitted products, the sensitivity sequence and contribution sequence of quantitative product P in n industries are calculated to provide support for customers to select quantitative products.

[0044] Specifically, the implementation steps are as follows:

[0045] Step 1: Determine in advance the n industries involved in the quantitative product P. The industry sequence is:

[0046] I={I1,I2,……I n

[0047] Step 2: For Industry I i , based on the business scenario, select the m most representative products and get the industry I i The representative quantitative product sequence of

[0048]

[0049] The elements Indicates that Industry I i The jth representative product of .

[0050] Step 3: Divide the profit range:

[0051] Determine the overall time range of the data to be processed by the quantitative product [S,E].

[0052] According to the preset profit interval segmentation length w and step length dt, the profit segmentation of the time range interval [S, E] is carried out according to the following rules:

[0053] The first interval is: [S, S+w];

[0054] The kth interval is: [S+(k-1)*dt,S+(k-1)*dt+w];

[0055] Where: k ≥ 2, S + (k-1) * dt + w ≤ E;

[0056] Step 4: Divide the time range interval [S, E] according to step 3 to obtain t time slice sequences T = {T1, T2, ..., T t};

[0057] Step 5: Calculate the interval rate of return:

[0058] a. Calculate the quantized product P at each time slice T i The interval yield of , thus obtaining the interval yield sequence of the quantitative product P:

[0059]

[0060] b. Calculate the number of products in a set of m products in any industry i In each time slice T i The interval rate of return of the product The interval return series of:

[0061]

[0062] Step 6. According to step 5, we can get the interval yield matrix of m products in n industries in each time slice:

[0063]

[0064] Among them, the matrix element p i,j,k Represents the interval rate of return of the j-th product in the i-th industry in time slice k.

[0065] Therefore, for n industries, there are n interval return matrices P i,m,t , one matrix for each industry.

[0066] Step 7: Based on the attributes, business scenarios, business experience, industry attributes and other factors of specific quantitative products, preset the weight sequence W of m products in each industry. Use the linear regression model to train all products in any industry i, select m products that meet the set regression threshold, and repeatedly train them in combination with business scenarios to finally obtain the sequence value that meets business needs:

[0067] W={w1,w2,…w i …w m},in, And, 0<w i <1;

[0068] Step 8: Combine matrix P i,m,t , weight sequence W, get the fitting product P of industry i i In each time slice T k The return sequence of:

[0069]

[0070] Among them, the sequence P′ i Any element P′ h for:

[0071]

[0072] Step 9: According to step 8, obtain the yield sequence of the fitting product of each industry i in n industries, so as to obtain the industry fitting product in the time series T = {T1, T2, ... T t The return matrix is ​​as follows:

[0073]

[0074] Among them, the element p of the matrix N i,j Represents the rate of return of the ith industry in time slice j.

[0075] Step 10: Calculate industry sensitivity: Based on the above, we can get the quantitative product yield sequence:

[0076] The matrix of product yields for n industries:

[0077]

[0078] Substitute into the following regression equation:

[0079]

[0080] in, And, 0<w′ i<1, ε is the compensation residual value; through the regression equation calculation, the sensitivity w′ of the quantitative product P in industry i is obtained i .

[0081] w′ i The larger the value, the more sensitive product P is to industry i. When industry i changes, the greater the disturbance to the revenue of product P.

[0082] Step 11: Based on step 10, obtain the sensitivity sequence of product P to n industries:

[0083] W′={w′1,w′2,…w′ i …w′ n}

[0084] Based on the fitted product yield matrix obtained in step 9:

[0085]

[0086] Get the yield sequence: N′={p′1,p′2,…p′ i …p′ n};

[0087] Among them, the element p′ of the yield sequence N′ i is the mean of the elements of the N rows of the matrix, that is:

[0088]

[0089] Step 12: Calculate the industry contribution sequence: Q = {q1, q2, ...q i …q n}={w′1*p′1, w′2*p′2,…w′ i *p′ i …w′ n *p′ n}, where the element q in the sequence Q i That is, the contribution of industry i to the yield of quantitative product P, q i The larger it is, the greater the contribution of industry i to the revenue of product P.

[0090] Step 13: Through the industry sensitivity sequence W′={w′1,w′2,…w′ i …w′ n} and industry contribution sequence Q = {q1, q2, …q i …q n}, which can provide important decision-making basis for product selection.

[0091] Furthermore, the following are the assumptions of the embodiment: n=4 industries involved in the preset quantitative products, specifically: I={I1, I2, I3, I4}={agriculture, forestry, animal husbandry and fishery, steel, electronics, medicine and biology};

[0092] In actual applications, industries can use existing general industries or customize industries according to business needs. For the above four industries, select m=3 to represent products, and the product sequence table of each industry is as follows:

[0093] Table 1 Industry product sequence list

[0094]

[0095] The overall time range is selected as [S, E] = [20230101, 20230303], the interval length w = 1 month, and the step length dt = 7 days. Therefore, the intervals obtained by segmentation are:

[0096] [20230101,20230201], [20230108,20230208],

[0097] [20230115,20230215], [20230122,20230222],

[0098] [20230129,20230301]; that is, the time slice sequence: T = {T1, T2, T3, T4, T5}; the weight sequence W of m = 3 products in each industry is preset as: W = {w1, w2, w3} = {20%, 30%, 50%};

[0099] In practical applications, the weight sequence W needs to be determined based on factors such as industry experience and specific scenarios.

[0100] According to the industry sequence I, industry product sequence table, and time interval sequence T, the rate of return of each product in each industry in each time slice sequence is obtained:

[0101] Table 2 The rate of return of each product in each industry in each time slice series

[0102]

[0103] The data of each industry is the return matrix P of each product in the industry in the time interval series. i,m,t , quantify product sequence Combine the weight sequence W = {w1, w2, w3} = {20%, 30%, 50%} and the various yield matrices P in step 1) i,m,t , calculated according to the following formula, we can get the fitting product P of each industry i i In each time slice Tk The return sequence of:

[0104]

[0105] Among them, the sequence P′ i Any element P′ h for:

[0106]

[0107] For example: The rate of return of the fitted product of the industry <Agriculture, Forestry, Animal Husbandry and Fishery> in the time interval T1 is: 0.2159*20%+0.0279*30%+0.2533*50%=0.1782.

[0108] Thus, we can get the yield matrix N of the industry fitting products in time series T:

[0109] Table 3 Fitting product yield matrix N

[0110] industry Fitting products Interval T1 Interval T2 Interval T3 Interval T4 Interval T5 Agriculture, Forestry, Animal Husbandry and Fishery X1 0.1782 0.4829 0.2957 0.5784 0.6702 Steel X2 0.4592 0.7356 0.6980 0.5427 0.7443 electronic X3 0.3669 0.4880 0.4432 0.4923 0.5835 medicine X4 0.6672 0.5874 0.4467 0.6896 0.6802

[0111] Return sequence of quantitative products Substitute the industry fitting product yield matrix N into the regression equation:

[0112]

[0113] in, And, 0<w′ i <1, ε is the compensation residual value; through the regression equation calculation, the sensitivity w′ of the quantitative product P in industry i is obtained i

[0114] Assume that the final calculated sensitivity sequence is:

[0115] W′={w′1, w′2, w′3, w′4}={0.2377,0.3465,0.1253,0.2905};

[0116] Calculate the mean of each column of the industry fitting product yield matrix N to obtain the yield sequence: N′={p′1,p′2,…p′ i …p′ n} = {0.4411, 0.6360, 0.4748, 0.6142};

[0117] The contribution degree sequence is obtained by performing the following calculations through the sensitivity sequence W' of the quantified product and the yield sequence N' of the fitted product:

[0118] Q={q1,q2,…q i …q n}=

[0119] w′1*p′1, w′2*p′2,…w′ i *p′ i …w′ n *p′ n ={0.1048, 0.2204, 0.0595,

[0120] 0.1784};

[0121] According to the sensitivity W′={0.2377,0.3465,0.1253,0.2905} and the contribution sequence Q={0.1048,0.2204,0.0595,0.1784}, it can be seen that for the quantitative product P,

[0122] The degree of influence of the given four industries on product p is from large to small: steel, medicine, agriculture, forestry, animal husbandry and fishery, and electronics;

[0123] The contribution of the given four industries to the revenue of product p is ranked from large to small as follows: steel, medicine, agriculture, forestry, animal husbandry and fishery, and electronics.

[0124] The present invention also provides a model building device for calculating the sensitivity and contribution of a quantitative product industry, which is characterized by comprising:

[0125] The representative quantitative product confirmation module is used to determine the n industries involved in the quantitative product P and select m representative quantitative products for each industry;

[0126] The yield calculation module is used to divide the pending yield intervals of the quantitative product P into t intervals and calculate each time slice T obtained by the segmentation. i The yield of t time slices is obtained by P , the return matrix P of m products in any industry i in each time slice i,m,t ;

[0127] The fitting product acquisition module is used to set the weight ratio of m products in any industry i, obtain the weight sequence W, and calculate the yield matrix P according to the yield matrix P. i,m,t The product of the weight sequence W is obtained by multiplying the fitted product P of any industry i i In each time slice, the yield sequence P′ i , thus obtaining the yield matrix N of the fitting products of any industry i in the time slice sequence T;

[0128] The sensitivity and contribution acquisition module calculates the sensitivity sequence and contribution sequence of the quantitative product P in n industries based on the obtained yield sequence of the quantitative product and the yield matrix N of the fitted product, providing support for customers to select quantitative products.

[0129] By using this device, the above-mentioned calculation processing method can be executed and the corresponding technical effects can be achieved.

[0130] An embodiment of the present invention also provides a computer-readable storage medium capable of implementing all the steps in the method in the above embodiment, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all the steps in the method in the above embodiment are implemented.

[0131] An embodiment of the present invention also provides an electronic device for executing the above method. As an implementation device of the method, the electronic device has at least a processor and a memory, and in particular, the memory stores data and related computer programs required for executing the method, such as storing set calculation programs, etc., and the processor calls the data and programs in the memory to execute all steps of the implementation method and obtains the corresponding technical effect.

[0132] Preferably, the electronic device may include a bus architecture, the bus may include any number of interconnected buses and bridges, and the bus will include various circuits linked together by one or more processors and memories. The bus may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are all well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the receiver and transmitter. The receiver and transmitter may be the same component, i.e., a transceiver, providing a unit for communicating with various other systems over a transmission medium. The processor is responsible for managing the bus and general processing, while the memory may be used to store data used by the processor when performing operations.

[0133] In addition, the electronic device may further include components such as a communication module, an input unit, an audio processor, a display, and a power supply. The processor (or controller, operation control) used may include a microprocessor or other processor device and / or a logic device, which receives input and controls the operation of various components of the electronic device; the memory may be one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory, or other suitable devices, which may store the above-mentioned related data information, and may also store a program for executing related information, and the processor may execute the program stored in the memory to realize information storage or processing, etc.; the input unit is used to provide input to the processor, for example, it may be a key or a touch input device; the power supply is used to provide power to the electronic device; the display is used to display display objects such as images and text, for example, it may be an LCD display. The communication module is a transmitter / receiver that sends and receives signals via an antenna. The communication module (transmitter / receiver) is coupled to the processor to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal. Based on different communication technologies, multiple communication modules may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless local area network module, etc. The communication module (transmitter / receiver) is also coupled to a speaker and a microphone via an audio processor to provide an audio output via the speaker and receive an audio input from the microphone, thereby realizing a common telecommunication function. The audio processor may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor is also coupled to a central processor, so that recording can be performed on the machine through the microphone, and the sound stored on the machine can be played through the speaker.

[0134] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0135] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0136] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0137] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in a box or multiple boxes. Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0138] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention 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 model construction method for calculating the sensitivity and contribution of a quantitative product industry, characterized in that: include: S1. Determine the n industries involved in the quantitative product P, and select m representative quantitative products for each industry; S2. Split the quantified product P into t intervals of pending revenue, and calculate each time slice T obtained by the splitting. i The yield of t time slices is obtained by P , the return matrix P of m products in any industry i in each time slice i,m,t ; S3, set the weight proportion of m products in any industry i, obtain the weight sequence W, according to the yield matrix P i,m,t The product of the weight sequence W is obtained by multiplying the fitted product P of any industry i i In each time slice, the yield sequence P′ i , thus obtaining the yield matrix N of the fitting products of any industry i in the time slice sequence T; S4. Based on the yield sequence P of the quantitative products obtained P The sensitivity sequence W′ and contribution sequence Q of the quantitative product P in n industries are calculated by the yield matrix N of the fitted product, providing support for customers to choose quantitative products.

2. The method according to claim 1, characterized in that The S2 specifically includes: determining the overall time range [S, E] of the quantitative product's pending profit interval, dividing the profit interval into sections according to a preset length w and a step length dt, wherein the first interval is: [S, S+w]; the kth interval is: [S+(k-1)*dt, S+(k-1)*dt+w], wherein: k≥2, S+(k-1)*dt+w≤E.

3. The method according to claim 1, characterized in that The method of obtaining the weight sequence W includes: combining the attributes of the quantitative products, using a linear regression model to train all products in any industry i, selecting m products that meet the set regression threshold, and assigning weights to the m products.

4. The method according to claim 1, wherein the sensitivity calculation of any industry i comprises: Quantitative product yield sequence: The matrix of product yields for n industries: Substitute into the following regression equation: in, And, 0<w′ i <1, ε is the compensation residual value; through the regression equation calculation, the sensitivity w′ of the quantitative product P in industry i is obtained i .

5. The method according to claim 1, characterized in that The step of obtaining the contribution sequence Q of the quantitative product P in n industries includes: obtaining a fitting product yield sequence N' according to a fitting product yield matrix N; The element p′ of N′ i is the mean of the elements in the N rows of the matrix, that is Thus, we can obtain the fitting product yield sequence N′={p′1,p′2,…p′ i …p′ n };q i =w′ i *p′ i ; Q={q1,q2,…q i …q n }={w′1*p′1,w′2*p′2,…w′ i *p′ i …w′ n *p′ n }, Among them, the element q in the contribution sequence Q i That is, the contribution of industry i to the yield of quantitative product P, q i The larger it is, the greater the contribution of industry i to the revenue of product P.

6. A model building device for calculating the sensitivity and contribution of a quantitative product industry, characterized in that: include: The representative quantitative product confirmation module is used to determine the n industries involved in the quantitative product P and select m representative quantitative products for each industry; The yield calculation module is used to divide the pending yield intervals of the quantitative product P into t intervals and calculate each time slice T obtained by the segmentation. i The yield of t time slices is obtained by P , the return matrix P of m products in any industry i in each time slice i,m,t ; The fitting product acquisition module is used to set the weight ratio of m products in any industry i, obtain the weight sequence W, and calculate the yield matrix P according to the yield matrix P. i,m,t The product of the weight sequence W is obtained by multiplying the fitted product P of any industry i i In each time slice, the yield sequence P′ i , thus obtaining the yield matrix N of the fitting products of any industry i in the time slice sequence T; The sensitivity and contribution acquisition module calculates the sensitivity sequence and contribution sequence of the quantitative product P in n industries based on the obtained yield sequence of the quantitative product and the yield matrix N of the fitted product, providing support for customers to select quantitative products.

7. The device according to claim 6, characterized in that The yield calculation module is also used to determine the overall time range [S, E] of the quantitative product's pending yield interval, according to the preset yield interval segmentation length w, step length dt, where the first interval is: [S, S+w]; the kth interval is: [S+(k-1)*dt, S+(k-1)*dt+w], where: k≥2, S+(k-1)*dt+w≤E.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

9. An electronic device, characterized in that: The invention comprises a processor and a memory; the memory is used to store a computer program; the processor is used to execute the method according to any one of claims 1 to 5 by calling the stored computer program.

10. A computer program product comprising a computer program and / or instructions, characterized in that: When the computer program and / or the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images