JP2014215715A - Device and method for analyzing change in market situation - Google Patents

Abstract

PROBLEM TO BE SOLVED: To analyze and evaluate the influence of a situational change and the effect of a measure in an active market where commodities or services of a plurality of categories or providers are supplied, competing each other.SOLUTION: The present invention detects a change in situation vector by: calculating a time series of situation vectors comprising a numeric value characterizing a rate of increase or decrease in market occupancy scale of each competition element at each point of time of time series data about the number of contracts of service categories and providers of each competition element; determining, for a given time interval, the simplicity of whether the time series of situation vectors can be considered to be a time series of vectors, in a designated time interval, which is constant in classification on a temporal axis; and, when determined to be simple, calculating, for each classification point of time at which the situation vector changes, the fundamental element of a situation change structure as a pair of situation change vectors which are a difference between situation vectors at the classification point of time and those before and after the classification point of time.

Description

  The present invention relates to a market situation change analysis apparatus and method, and more particularly, a consumer product in which a product itself or a product of the same standard or a similar standard is repeatedly or continuously used by the same individual, Or in the market for products such as systems or services, where competitors such as products, product categories, or operators that provide products compete for customer acquisition, and each competitor's market A situation where an increase or decrease in the occupation size occupied by a category or operator accelerates or decelerates due to changes in the market situation in an active market where the occupation size increases or decreases continuously. Change, detect the factors of acceleration or deceleration, estimate the contribution of each factor to acceleration and deceleration, and these factors that change the situation Market situation change analysis apparatus and method for analyzing the market situation or estimating the effectiveness and effect of market measures by analyzing the quantity that influences the market share size of the element and estimating the quantity that will affect the future About.

  In the product and service market, it is common for products of multiple categories and businesses to compete and compete for shares that occupy the market. In such a market, when a change occurs in the market share of a certain category or business operator, this is detected, and what kind of interaction or influence relationship occurs between the market share of each category or business operator. To understand the structure of the change in the situation, and what kind of changes have occurred in the market size occupancy so far, and what kind of change will affect the market occupancy in the future? If we can analyze and evaluate the impact of changes in the situation, we can execute market measures and judge changes more accurately and quickly. Thus, if there is a way to quantitatively estimate the structure of market changes and its impact on the past and the future, there is a high possibility of reducing lost opportunities and investment failures, thereby increasing the efficiency of the economy. Therefore, usefulness is great.

  For example, business operators often implement some measures against the market with the aim of increasing their categories and their share. At that time, whether there was a change in the market situation, if so, what kind of interaction or influence relationship has occurred in each category or business occupancy, and the interaction or influence relation concerned Analysis of the impact on the market so far, and by estimating how the market occupancy will change in the future, objective and early Can be evaluated. As a result, the efficiency of reducing the loss of investment and opportunities by deciding whether to continue the measure, and formulating a more effective measure afterwards is jeopardized.

  The market occupation scale of each category or business can often be known or estimated as time series data from public information or business management information of the business. However, it is generally not correct to regard the market share size as a market situation and to consider it as a change in the situation with an increase or decrease in the share size. This is because the general market is active, and customers constantly flow between each category, operator, outside the market, etc., and the market size of each category and operator continues to increase or decrease. Is. For this reason, it is difficult to consider that the market situation has changed due to the increase or decrease in the scale of occupation.

  In order to capture changes in market conditions, it is essential to correctly grasp what is a constant situation in an active market. To do so, it is necessary to understand the dynamics of continuous changes in market share size under certain circumstances. However, even if the situation has not changed, capturing the dynamics of market share in an active market has long been a difficult problem to solve. Only recently, the structure of the natural growth of the market, which is the basic problem, has been elucidated, and a theory explaining the difficulty of prediction has been submitted (see Non-Patent Document 1, for example). Based on this, the market growth is predicted (see Non-Patent Document 1, Patent Documents 1, 2, and 3). These are based on the assumption that the growth of a certain market as a whole (see Non-Patent Document 1 and Patent Document 1) and in the market where the categories compete, the power relationship of each category is constant and the situation does not change. Proposed a prediction method (see Patent Document 2). Therefore, it does not assume a change in the power relationship between categories or business operators, and does not propose a method for analyzing changes in the market situation. Based on the theory of Non-Patent Document 1, the current situation is to devise a method for quantitatively understanding the market situation concept, extracting the structure of the situation change based on this, and evaluating the impact It is a problem. Therefore, a method for extracting the structure of the situation change and a method for analyzing the market situation change and the effect of the market measure for estimating the influence of the situation change on the future occupation situation have not yet been obtained.

Japanese Patent No. 47777941 Japanese Patent No. 5001347 JP 2011-215989 A

S. Shimogawa, M. Shinno, and H. Saito, Structure of S-shaped growth in innovation diffusion, Physical Review E 85, 056121 (2012).

  The problems with respect to the above-described conventional technology are shown below.

  First, in a competitive active market, the problem is how to describe the situation regarding the market share of competitive factors as a quantitative variable, extract this from the data, and detect the change in the market situation as the change. . Hereinafter, this problem is referred to as a “first problem”.

  Second, in order to extract the structure of the situation change, it is necessary to extract the interaction or influence relationship between the competing elements from the change in the situation variable. Hereinafter, this problem is referred to as a “second problem”.

  Third, many products and services are generally offered to a large number of consumers such as the whole country or several regional blocks. Market conditions and changes are often different among subgroups such as regions and districts. In that case, the structure of the situation change is complicated, and it is difficult to extract it at the same time. Therefore, the structure of the situation change needs to be taken out so that the structure captured in the subgroup can be integrated into the whole, and using this, a method of integrating from the part into the whole needs to be provided. Hereinafter, this problem is referred to as a “third problem”.

  Fourthly, there is a need for a method for estimating the influence of the change in the situation by estimating how the structure of the changed situation in the extracted market will change the market share of each competing factor in the future. Hereinafter, this problem is referred to as a “fourth problem”.

  The present invention has been made in view of the above points. In an active market in which products or services of a plurality of categories and operators are provided and competing, the situation regarding the market share of competing factors such as each category and operators is shown. Quantitatively, based on this, the structure of the change in the situation is extracted as an interaction or influence relationship between the competing elements, and the change of the situation change in the future estimates the change in the future occupation situation. It is an object of the present invention to provide a market situation change analysis apparatus and method capable of analyzing situation changes and measure effects.

In order to solve the above-mentioned problems, the present invention (Claim 1) is a product for consumers in which the product itself or a product of the same standard or a similar standard is repeatedly or continuously used by the same individual. Or, in the product market that includes systems or services, when the product, product category, or the company that provides the product competes for customer acquisition, the market share of each competing factor continuously increases Or a market situation change analysis device for analyzing a changing trend of an active market,
Employer number data storage means for storing time series data of service categories of each competing factor and the number of contracts of the operators,
Situation vector calculation means for calculating a time series of situation vectors consisting of numerical values characterizing the rate of increase or decrease of the market share of each competitive element at each time of the time series data;
And a situation change detecting means for detecting a change of the situation vector for a given time interval.

The present invention (Claim 2) provides the situation change detecting means,
Simplicity determining means for determining the simplicity of whether or not the time series of the situation vector can be regarded as a vector time series that is piecewise constant on the time axis within the specified time interval;
In the simplicity determination means, when it is determined that the time series of the situation vector is simple within a specified time interval, for each division time when the situation vector changes, the division time point and the division And simple decomposition construction means for calculating a basic element of the situation change structure as a pair of situation change vectors which are the difference of the situation vectors before and after the time.

Further, the present invention (Claim 3) provides the simple disassembling construction means,
For the specified competing element and the basic element of the specified situation change structure, the difference in the rate of increase or decrease of the market share of the competing element before and after the time point of the change in the situation belonging to the basic element is calculated. Basic decomposition calculation means for decomposing as a sum of acceleration amount or deceleration amount for each factor of speed change is included.

Further, the present invention (Claim 4) is the simple disassembling construction means,
When it is determined that the time series of the situation vector is simple in the time interval for the specified time interval, each situation having a segment time point in the time interval for the specified competing element By adding the results of the basic decomposition by the basic elements of the change structure, the difference in the speed of increase or decrease in the market share of the competitive element at both ends of the time interval is taken as the sum of the acceleration or deceleration of each factor. Further, simple disassembly configuration control means for disassembling is provided.

Further, the present invention (Claim 5), for the division of the specified customer population, means for calculating a time series of the situation vector amount under the divided customer sub-group,
It is detected whether the time series of the situation vector amount under each small group is simple for the specified time section. A means of determining the semi-simpleness of the situation change that is determined to be semi-simple;
If it is determined that it is semi-simple for the specified time segment and the specified customer population split, for each of the segmented customer sub-groups, the specified competing factor and the corresponding time segment are simple. By performing the disaggregation and summing the results across the entire customer sub-group, the difference in the rate of increase or decrease in the market share of the competing factors at both ends of the time interval can be reduced or decelerated. A semi-simple decomposition construction means for decomposing as a sum of quantities and extracting a structure of semi-simple situation change;
It has further.

  Further, according to the present invention (Claim 6), in the simple decomposition construction means, as a logarithmic speed determined as an increase or decrease in the market share size of each competing element per unit time on the logarithmic time axis, Means for calculating an element of the situation vector.

  Further, according to the present invention (Claim 7), in the simple decomposition construction means, for the designated time interval and the designated competitive element, the time of the increase or decrease rate of the market share size of the competitive element is concerned. When the difference at both ends of each subsection of the section is decomposed as the sum of the acceleration of each factor, the evaluation time length is changed from the end time of the specified time section to the end time for the specified evaluation time length. At each time point from the start of the designated time interval to the end of the evaluation time length when the logarithmic growth is followed until the added time, each change in the situation with respect to the market share size of the competing factor A means for calculating the influence amount of the factor is included.

  In the product and service market, it is common for products of multiple categories and businesses to compete and to compete for shares that occupy the market. In such a market, when a change occurs in the market share of a certain category or business operator, this is detected, and what kind of interaction or influence relationship occurs between the market share of each category or business operator. If it is possible to know the structure of the change in the situation and whether the impact relationship that has occurred can affect the market occupancy in the future, the impact of the change in the situation can be understood. Make more accurate and quick decisions.

  According to the present invention, when the situation change has a semi-simple nature, the situation regarding the market share of the competitive element such as each category or business operator is quantitatively grasped, and the structure of the situation change is determined based on the interaction between the competitive elements. Or extract it as an acceleration factor decomposition of the logarithmic speed change of the influence relationship or the competing factor of interest, and evaluate the effectiveness of the measure by this, and also change the change to the previous and future occupation situation along the structure of the situation change Analyzing and estimating increases the chances of reducing lost opportunities and investment failures, and makes the economy more efficient.

It is a lineblock diagram of a market situation change analysis device in one embodiment of the present invention. It is a flowchart of operation | movement of the market situation change analysis apparatus in one embodiment of this invention. It is a flowchart of the broken line model set preparation part in one embodiment of this invention. It is a flowchart of operation | movement of the simple decomposition | disassembly structure control unit in one embodiment of this invention.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

  The outline of problem solving is described below. First, we will apply a new theory of S-shaped growth in the spread of innovation that has recently advanced. The natural growth of the market is thought to be regarded as the spread of innovation, and research that captures and explains the S-shaped growth has been enormous in the past. They could not explain the S-shaped growth data properly and ended up unsuccessfully, but in recent years, a theory that finally succeeds in this has been submitted (Non-Patent Document 1). It has been used for prediction and the like (Non-Patent Document 1, Patent Documents 1, 2, and 3). Therefore, these technologies are applied to give a quantitative expression to the market share in the active market.

  According to the theory, the information propagation flow of the innovation that forms the market is structured in society, and the structure of the inflow velocity distribution of the information on the learning channel of the prospective employer follows two power law with different indices. Individual recruitment behavior can be described by a model in which the cumulative amount of learning information exceeds a constant threshold. According to this theory, even in a competing market, there is a possibility that the basic structure of information propagation in which each competing factor affects the customer's recruitment behavior is shared and constant. In this case, if there is a certain situation, it is highly possible that the main part of the growth or decay of the customer occupation scale of each competitive element can be described by a logarithmic function of time sharing a certain origin. Therefore, by introducing a logarithmic time axis, there is a possibility that a plurality of nonlinear natural increase / decrease curves can be linearized simultaneously.

  In this case, the simultaneous linearization characterizes the growth or decay of the customer occupancy scale of each competing element in a constant situation with a logarithmic function of time. This coefficient is called “logarithm growth rate of customer occupancy scale” or simply “speed”. The market situation will be expressed as a vector constructed by taking this speed for each competing factor. This is the situation vector, and thereby the first problem 1 is solved. That is, the change in the situation is detected as a change in the situation vector composed of the speed. Since the growth of a new factor follows an S-shaped curve, a small first half of the S-shape may appear before it settles to logarithmic growth, and it may take some time. For this reason, a market-occupied-scale time-series model based on a broken line on the logarithmic axis and a situation vector model having a piecewise constant function as an element are accompanied by places that do not coincide with the data locally.

  Next, for the second problem 2, the structure of the situation change is extracted by using the market situation expression by the logarithmic velocity vector. Individual changes in the market situation are usually due to changes in certain measures and the spread of external factors, so the situation changes are considered to work simultaneously in a certain region, for example, and the situation remains constant before and after. At this time, the situation change is represented by a pair of changes in the velocity vector at a certain time. This is called “acceleration vector with acceleration point”. An acceleration vector with an acceleration point is a basic element that constitutes a change in situation. In general, since it takes a little time to settle from one logarithmic growth to the next logarithmic growth, in order to reproduce the line graph on the logarithmic time axis, the acceleration point of the acceleration vector with the acceleration point is a line. Take the crossover point. For this reason, the said time point generally differs from the acceleration start time and the start time of the next logarithmic growth.

  The acceleration vector represents an interaction or influence relationship between competing elements in the situation change. One situation change is usually considered to be caused by one competing factor. This is due to the generally absorptive (stolen customers from other competing factors) or outflowing (customer to other competing factors) effects in the relationship between each customer and the competing factor. Therefore, the acceleration vector takes a form in which a star-shaped outflow or absorption relationship from the same competing element is superimposed on the relation between the competing element and other competing elements. The center of this star is called the source of action. In the case of a major change that changes the market structure, the direction of this action is considered to be the same regardless of the customer. In this case, it is considered that the relational graph representation of the acceleration vector is not a binary combination of superposition of outflow or absorptive relations, but often has a unitary action of either absorptive or outflow. When such a situation change factor does not work simultaneously, by examining non-zero elements of the acceleration vector, if the number of factors is three or more, a competing element that acts as an action source can be identified from the data of each situation change. When there are two non-zero elements in the acceleration vector, a star shape is not formed, but when there is a competing element of interest, for example, in-house service, the competing element is obvious as a partner that has caused a speed change in the competing element of interest. Identified. If the basic elements of the situation change structure are given, the speed difference at the time of the situation change of the competing element of interest is decomposed as the sum of accelerations with the factor of competition as a subscript. This is called “basic decomposition” by basic elements. Here, the acceleration is assumed to have a negative sign and includes deceleration.

  When the acceleration vector element is only the competing element of interest, the acceleration factor is not in the set of the competing elements being measured, but outside the measurement. On the other hand, if the sum of the acceleration vectors disappears, it means that the situation has changed, limiting to the range of competing elements that are non-zero as elements of the acceleration vector. In this way, the influence range of interaction can be taken out.

  Considering a certain time interval, it is assumed that a speed change has occurred for a competing element of interest due to some changes in the situation within this time interval. This speed change can be decomposed as the sum of accelerations with the competing elements as subscripts because the factors are specified. This factorization is called “speed change” or “simple acceleration decomposition”. The reason for calling it simple decomposition will be described below. The above is the approach for solving the second problem.

  Next, the third problem will be described. Typically, market conditions and their changes are in different situations between a subset of customers such as regions and districts. Therefore, even if the logarithmic time described above is taken, the time series of the market share size of the competing elements may not be broken but become a curve. On the other hand, the situation change to which the polygonal line model applies is called “simple”. In a simple situation change, acceleration factor decomposition for a speed change of the competing element of interest can be obtained by simple decomposition as described above.

  If the situation change is not simple, the structure of the situation change cannot be directly extracted by the acceleration vector with acceleration time point, that is, the basic element of the situation change structure, and the speed change cannot be decomposed into the acceleration factor by simple decomposition. . At this time, when the original customer set is divided and limited to a subset, the situation change may be simple. That is, this is a case where the time series of the market share of each competitive element is broken by logarithmic time. In this case, first, the speed change of the competing element of interest is decomposed into acceleration factors by simple decomposition on a subset. Here, since the function that associates the logarithmic growth rate with the time series of the market size growth of each competitive element is a linear function, the equation for accelerating factorization of speed change constructed for each subset Is added across each subset, so that the acceleration factor decomposition of the speed change in the original set can be obtained, and the structure of the situation change can be analyzed. A situation change that is simple with respect to the division of a certain customer group is called "semi-simple". As described above, the structural analysis of the semi-simple situation change can be reduced to the simple structural analysis of the situation change by the linearity of the logarithmic velocity function. This process is called “semi-simple decomposition of the situation change structure”.

  Next, the fourth problem will be described. The factor decomposition of the speed change extracted by “simple decomposition” or “semi-simple decomposition” indicates how much the growth rate of the market share scale has changed by what factor. This gives a quantitative understanding of the current changes in circumstances. For example, it teaches the effectiveness of measures to increase the market share of competing factors of interest, the priority of countermeasures against slowing the growth rate, and so on. On the other hand, if the situation changes in the competitive market, the influence may cause a change different from the previous one due to the market share of the competitive element. Thus, knowing the impact of changes in the market on the market share is the main goal of the change analysis.

  The market situation can change not only in the area where the data was taken, but also thereafter, but there is currently no known method for estimating the situation change consisting of discontinuous speed changes. Therefore, if it is assumed that there will be no new changes in the situation in the future, a time-series change of how the market share size changes can be configured by using the velocity vector representing the situation. In actual market growth, discontinuous final demand limits can arise, but these limits are also difficult to predict. Therefore, a time-series change due to logarithmic growth is configured on the assumption that the final demand limit is not reached.

  Here, when the situation has changed over a period of time in the past, the information that decomposes the speed change at both ends of the time interval into acceleration factors does not show the impact on the change in market size that occurred during that time, For the past, the impact scale is evaluated in time series. If the speed change amount is decomposed in a small time interval, a time series of speed changes for each factor can be obtained, and if this is accumulated, the influence amount on the market occupation scale can be analyzed for past time points. In the prediction, each factor of the situation change can sequentially calculate the amount by which the market share of each competitive element is increased or decreased in the estimation of the subsequent time series change. From this, it is possible to structurally analyze and evaluate the influence of the situation change.

  This will be specifically described below.

  In the following, fixed-line and wireless broadband services and Internet use by smartphones are expected to grow in the future. For example, when a continuous record of the number of subscribers of each competitive service category and target business operator is collected by prefecture in a certain regional block consisting of several prefectures, An example of a system that analyzes situation changes and measure effects will be shown.

  FIG. 1 shows a configuration of a market situation change analysis apparatus according to an embodiment of the present invention.

  The market situation change analysis apparatus 100 shown in the figure is connected to a user interface 200, an employer number data storage unit 300, and an output storage unit 400.

  The market situation change analysis apparatus 100 includes a user interface processing unit 101, a display control unit 102, a central control unit 103, a main memory 104, a basic setting execution unit 110, a logarithmic time origin setting unit 120, a logarithmic time conversion unit 130, and a polygonal line model set. A creation unit 140, a simple decomposition configuration unit 150, a semi-simple decomposition configuration unit 160, and a situation change influence analysis evaluation unit 170 are included.

  The user interface processing unit 101 receives a command for the user of this system to control the system and execute target analysis, transfers the command to the central control unit 103, and executes a display command from the central control unit.

  The display control unit 102 displays data based on the display command processed by the central control unit 103.

  The central control unit 103 controls the flow of commands, messages, and data from each unit.

The recruitment number data storage unit 300 inputs and stores data in a time series of the number of contracts in each sub-division (for example, prefecture) of a target service category and business operator from the outside, and stores data in response to a call. Forward. The data stored in the recruitment number data storage unit 300 is durable or contractual, where the market competes in a certain region that can be divided into several sub-regions Fi, i = 1, 2,. Adoption of each product category Ci, i = 1,2, ..., A, under the product category (for example, FLET'S Hikari (registered trademark), au Hikari (registered trademark), cable TV, WiMAX, etc.) Time series data of the time interval [T ₀ , T ₁ ] up to a certain time in the past for the number NF _i C _j i = 1,2, ..., G, j = 1,2, ..., A, DF _i C _j = {(t _k , NF _i C _j (t _k )), k = 1,2, ..., n}, i = 1,2, ..., G, j = 1,2, ..., A Is stored. In addition, products or operators E _j belongs to one of each product category, j = 1,2, ..., B , the number of adopters of each region of the _{NF i E j, i = 1,2} , ..., G, j Time series data DF _i E _j = {(t _k , NF _i E _j (t _k )), k = 1,2, ... for time interval [T ₀ , T ₁ ] for B = 1, 2,. , n}, i = 1, 2,..., G, j = 1, 2,.

  For example, in a certain district consisting of several prefectures, for a plurality of categories of a contract-based service, the time-series data for each quarter of the number of users by prefecture with which one of them is contracted, and these For the above-mentioned service providers that provide services belonging to any of the service categories, time-series data for each quarter of the number of users by prefecture with which the service is contracted is stored.

  Below, the process of the principal part of the market situation change analysis apparatus 100 is demonstrated.

  FIG. 2 is a flowchart of the operation of the market situation change analysis device according to the embodiment of the present invention.

The basic setting execution unit 110 provides a function for setting various parameters and specification requests for each unit and a target of interest, and executes a function for displaying, inputting, and saving a file for a setting request table for defaults and basic settings. Minimum time unit such as quarter or month, origin of logarithmic time, data time interval [T ₀ , T ₁ ], threshold 1 used for error determination and threshold 2 used for determination of interval division limit, line model Setting of step value δ at the time of creation of division point candidate in creation, setting of target service category or operator, setting of time interval “T ₂ , T ₃ ” for extracting situation change, final evaluation to evaluate the influence of situation change performs setting of the time T ₄ (step 110).

  The logarithmic time origin setting unit 120 sets the logarithmic time origin from the data using the invention of Patent Document 1 (step 120).

The logarithmic time conversion unit 130 executes processing for converting the time axis of each contractor number time series data in the employer number data storage unit 300 into a logarithm (step 130). Specifically, the time series [T ₀ , T ₁ ] is specified as the time series [T ₀ , T ₁ ] of the specified product category of the small district specified via the user interface 200 or the number of employers of the specified business operator. Change to logarithmic time in a specific time interval. For example, the time series data of the number of employers in the employer number data storage unit 300 is
D = {(N (t _i i), t _i , i = 1,2,… n}
Then, in contrast to this, data with logarithmized time
DL = {(N (t _i ), log (t _i )), i = 1,2,…, n}
Is calculated.

  The polygonal line model set creation unit 140 executes a process of approximating the logarithmic time series data of each number of contractors by prefecture logarithmized by the logarithmic time conversion unit 130 with a polygonal line model in a specified time interval. For the time series data converted into logarithmic time by the logarithmic time converter 130, an approximation procedure using a polygonal line is executed (step 140).

  A flowchart of the process of the polygonal line model set creation unit 140 is shown in FIG.

  The polygonal line model set creation unit 140 sets the target sections as all sections (step 100). First, a regression line is calculated for each of the target sections (step 101), and the sum of the mean square error of the regression line for each segment and the data graph DL is taken as an error (step 102). If the error exceeds the preset threshold value 1 (step 103, Yes), the specified step value δ is used to select a new division point candidate from the start point of the section to the end point of the section. While moving (step 104), a regression line is created in each of the divided two sections (step 105), and the point where the sum of the square errors is minimized is divided as a new division point. A new section is set (step 106). If the error is less than or equal to the threshold value 1 (step 103, No), the process proceeds to step 107. If the minimum width of the line segment section of the broken line is smaller than the threshold value 2 (step 107, Yes), it is determined that creation of the broken line model has failed (step 108). If not (No at Step 107), the process proceeds to Step 101.

  The polygonal line model set creation unit 140 that performs the above operation includes a regression line calculation unit 141, a new segment point creation unit 142, and a single polygonal line model creation control unit 143.

  The regression line calculation unit 141 calculates a regression line and its squared error value for the specified time interval as one segment of the broken line and the specified logarithmic time contractor number time series data (step 102), and the mean square error Output along with the number of data points used to calculate the value.

  The new dividing point creation unit 142 creates a dividing point candidate group using the step value δ within the specified time interval for the specified time interval and the specified logarithmic time contract number time series data, and the regression line calculation unit 141. Are repeatedly used to introduce a new segment point that minimizes the sum of squared errors of each regression line in two segments generated by each segment point candidate (step 106).

  The single line model creation control unit 143 uses the specified time interval and the specified logarithmic time contract number time series data as an initial interval, evaluates the mean square error, and returns a regression result having a large square error until the error threshold value 1 is not exceeded. The new division point creation unit 142 is called for the section of and the operation for creating a new division point is repeated. Even if the error threshold 1 reaches the division limit due to the segment points, if the threshold value is not less than the threshold value 1, a failure to create a polygonal line model is notified, and if it is less, a regression line group arranged in order of segment points and sections is output (step 107).

  For the designated prefecture, the simple decomposition composition unit 150 obtains the target competing element, that is, the simple decomposition vector regarding the increase rate of the number of employers of the specified service category or business, and the acceleration factor decomposition vector sequence with acceleration time point. Calculate (step 150).

  Details of the simple disassembly unit 150 will be described later.

The semi-simple decomposition composition unit 160 calculates the vector sum of the output of simple decomposition configured in each prefecture over the entire district, and calculates the speed change of the competitive element of interest at both ends of the designated section “T ₂ , T ₃ ” of the situation change analysis. The semi-simple decomposition and the semi-simple decomposition of the speed change of the competing element of interest for any given subsection [s, s + ds] in [T ₂ , T ₃ ] are calculated. In this process, in this process, if the simple disassembly unit 150 is called in each prefecture and, as a result, a determination result indicating that the situation change in the prefecture is not simple is output, the situation change is not semi-simple. The determination result is output (step 160).

The situation change impact analysis and evaluation unit 170 repeatedly calls the simple decomposition configuration unit 150 for each prefecture and outputs a determination result of simplicity. For the prefecture that was a simple determination, for each minimum time interval unit, Calculate the output β (ds) of simple decomposition of the speed change of the competitive element of interest, and use the time series of the evaluation time interval [T ₂ , T ₄ ] as a structural analysis of the influence of the situation change

を出力する。また地区全体に対しては、半単純分解構成部１６０を呼び出し、半単純性の判定結果を出力し、半単純の判定であった場合に、最小時間区間単位毎に、着目競合要素の速度変化の単純分解の出力β(ds)を算出し、情勢変化の影響の構造的分析として評価時間区間[T₂,T₄]の時系列

Is output. In addition, for the entire district, the semi-simple decomposition configuration unit 160 is called, and the determination result of semi-simpleness is output. If the determination is semi-simple, the speed change of the competing element of interest for each minimum time interval unit. Time series of the evaluation time interval [T ₂ , T ₄ ] as the structural analysis of the influence of the situation change

を出力する（ステップ１７０）。

Is output (step 170).

  Below, the simple decomposition | disassembly structure part 150 is demonstrated.

  The simple decomposition configuration unit 150 includes a timed acceleration vector extraction unit 151, a basic decomposition calculation unit 152, and a simple decomposition configuration control unit 153.

The point-in-time acceleration vector extraction unit 151 is designated as included in the time interval [T ₀ , T ₁ ] from a line model based on a logarithmic time axis of the number of employees in each product category and each operator's designated small district. The polygonal line model set creation unit 140 is called with respect to the determined time interval, and the acceleration vector α _i at each broken point t _i in the specified time interval is calculated using the broken line model set as an input. Output as {(t _i , α _i ), i = 1, 2, ..., h ₀ }.

  For example, the inclination of the polygonal line is extracted from the set of the polygonal line models of each product category and each business operator obtained by executing the polygonal line model set creating unit 140, and the vector By using elements, the time series of the situation vector is calculated. Further, by calculating the difference between the time point of each broken line and the situation vector before and after that time point, a pair of acceleration time point and acceleration vector, which is a basic element of situation conversion, is obtained.

  The basic decomposition calculation unit 152 calculates the acceleration factor decomposition vector β of the speed change of the competing element at the time point from the given acceleration vector α.

  The basic decomposition calculation unit 152 calculates a basic decomposition of a speed change at an increasing rate of the number of employers with respect to a specified specified product category or a business belonging to the specified product category and a basic element of a given situation change. .

For example, it is assumed that the basic element of the designated situation change is a pair of acceleration time t and acceleration vector α. For the sake of simplicity, the focus is on the business E ₁ belonging to the product category C ₁ and the market is divided by product categories that are all in an exclusive relationship without considering other businesses. . The component of the vector α corresponding to the product category C ₁ is described as <α, C ₁ > the component of the business operator as <α, E ₁ >. Note that the vector α is a vector in a number space defined by arranging components.

First, let α ′ be a vector obtained by replacing the component <α, C ₁ > with <α, C ₁ > − <α, E ₁ > in the acceleration vector α. <Α, C ₁ > − <α, E ₁ > is referred to as an intra-category competition component because it represents the acceleration amount of the total of other businesses in the product category to which the business operator belongs.

Next, the sum <α ′> of the components of the vector α ′ is taken, and the sign is inverted to be − <α ′>, and a vector obtained by expanding the vector α ′ is defined as α ″ as a new component. The number of components in α ″, that is, the dimension of the number space to which it belongs is one greater than the number of components in vector α ′. -<Α '> represents the amount of acceleration outside the market. First, if <α, E ₁ > is regarded as zero, the basic decomposition of the speed change of E ₁ , that is, the vector β representing the acceleration factor decomposition is taken as a zero vector. Next, it is assumed that the component <α, E ₁ > is non-zero. Note that the number of non-zero components of α ″ is two or more. If the number of α ″ zero components is exactly 2, then β is a vector with the components from α ″ to E ₁ being zero. At this time, the number of non-zero components of β is one. Next, it is assumed that the number of non-zero components of α ″ is three or more. It is assumed that the code structure is not a star shape, that is, the number of positive or negative sign components is not one. At this time, it is considered that the interaction is not separated, and a warning is given that the relevant basic element has a singularity consisting of simultaneous occurrence of the interaction, and the sign opposite to <α, E ₁ > in α " A vector obtained by multiplying the components other than the above by zero and further multiplying by a constant so that the sum is − <α, E ₁ > is set as a vector β representing acceleration factor decomposition of E ₁ .

Next, when the sign configuration of α ″ is a star shape, if the center, that is, the component with a positive or negative sign is one and the corresponding component is E ₁ , β is changed from α ″. E Define the component of ₁ as a vector with zero. If the center is not E ₁ , β is calculated as a vector that is zero except for the component at the center, and the value of that component is − <α, E ₁ >.

  The operation of the simple disassembly configuration control unit 153 will be described.

  FIG. 4 is a flowchart of the operation of the simple decomposition configuration control unit according to the embodiment of the present invention.

The simple decomposition configuration control unit 153 calls the time-accelerated acceleration vector extraction unit 151 to output the sequence {(t _i , α _i ), i = 1, 2,..., H ₀ } (step 151). Each element is extracted (step 152), the basic decomposition calculation unit 152 is repeatedly called (step 153), and the basic element of the situation change having the acceleration point in the time interval [T ₀ , T ₁ ] is extracted, and the new sequence {(t _i , β _i ), i = 1, 2,..., h} are created (step 154). Here, elements for which the acceleration factor vector β _i is zero are removed from the series.

Next, as a decomposition of the speed change of the competitive element of interest at both ends of the specified interval [T ₂ , T ₃ ] of the situation change analysis, each of {(t _i , β _i ), i = 1, 2,…, h} A vector summing up the acceleration factor vectors β _i is calculated (step 155). In addition, for any given subsection [s, s + ds] in [T ₂ , T ₃ ], a basic decomposition element having an acceleration time t _i in the section [s, s + ds] ( β (ds) is output as the sum of the acceleration factor vectors β _i of t, β _i ) (step 156). In this process, the polygonal line model set creation unit 140 is called and, as a result, if the creation of the polygonal line model has failed, a determination result that the situation change in the prefecture is not simple is output.

  Further, the present invention constructs the operation of each component of the market situation change analysis device shown in FIG. 1 as a program and installs and executes it on a computer used as the market situation change analysis device, or via a network It can be distributed.

  The present invention is not limited to the above-described embodiment, and various modifications and applications can be made within the scope of the claims.

DESCRIPTION OF SYMBOLS 100 Market situation change analysis apparatus 101 User interface process part 102 Display control part 103 Central control part 104 Main memory 110 Basic setting execution part 120 Logarithmic time origin setting part 130 Logarithmic time conversion part 140 Polygonal line model set creation part 141 Regression line calculation unit 142 New division point creation unit 143 Single broken line model creation control unit 150 Simple decomposition configuration unit 151 Timed acceleration vector extraction unit 152 Basic decomposition calculation unit 153 Simple decomposition configuration control unit 160 Semi-simple decomposition configuration unit 170 Emotional change influence analysis evaluation unit 200 User interface 300 Employer count data storage unit 400 Output storage unit

Claims (8)

A product, or product category, in a product market that includes a consumer product or system or service where the product itself or a product of the same or similar standard is used repeatedly or continuously by the same individual, or Market conditions that analyze changes in active market conditions where the market share of each competing factor is continually increasing or decreasing when the product provider competes for customer acquisition A change analysis device,
Employer number data storage means for storing time series data of service categories of each competing factor and the number of contracts of the operators,
Situation vector calculation means for calculating a time series of situation vectors consisting of numerical values characterizing the rate of increase or decrease of the market share of each competitive element at each time of the time series data;
A market situation change analysis device, comprising: a situation change detection means for detecting a change in the situation vector for a given time interval. The situation change detecting means includes
Simplicity determining means for determining the simplicity of whether or not the time series of the situation vector can be regarded as a vector time series that is piecewise constant on the time axis within the specified time interval;
In the simplicity determination means, when it is determined that the time series of the situation vector is simple within a specified time interval, for each division time when the situation vector changes, the division time point and the division Simple decomposition composition means for calculating basic elements of the situation change structure as a pair of situation change vectors which are the difference of the situation vectors before and after the time point;
The market situation change analysis device according to claim 1, comprising: The simple disassembling means is
For the specified competing element and the basic element of the specified situation change structure, the difference in the rate of increase or decrease of the market share of the competing element before and after the time point of the change in the situation belonging to the basic element is calculated. 3. The market situation change analysis device according to claim 2, further comprising basic decomposition calculation means for decomposing as a sum of acceleration amount or deceleration amount for each factor of speed change. The simple disassembling means is
When it is determined that the time series of the situation vector is simple in the time interval for the specified time interval, each situation having a segment time point in the time interval for the specified competing element By adding the results of the basic decomposition by the basic elements of the change structure, the difference in the speed of increase or decrease in the market share of the competitive element at both ends of the time interval is taken as the sum of the acceleration or deceleration of each factor. 4. The market situation change analysis device according to claim 3, further comprising simple decomposition configuration control means for decomposing. Means for calculating a time series of situation vector quantities under the divided customer sub-groups for the division of the specified customer population;
It is detected whether the time series of the situation vector amount under each small group is simple for the specified time section. A means of determining the semi-simpleness of the situation change that is determined to be semi-simple;
If it is determined that it is semi-simple for the specified time segment and the specified customer population split, for each of the segmented customer sub-groups, the specified competing factor and the corresponding time segment are simple. By performing the disaggregation and summing the results across the entire customer sub-group, the difference in the rate of increase or decrease in the market share of the competing factors at both ends of the time interval can be reduced or decelerated. A semi-simple decomposition construction means for decomposing as a sum of quantities and extracting a structure of semi-simple situation change;
The market situation change analysis device according to claim 4, further comprising: The simple disassembling means is
6. A means for calculating an element of a situation vector at each time point as a logarithmic speed determined as an increase or decrease in the market share size of each competing element per unit time on a logarithmic time axis. 1. Market situation change analysis device according to item 1. The simple disassembling means is
For the specified time interval and the specified competing factor, the difference in the speed of increase or decrease of the market share of the competing factor at both ends of each sub-interval is decomposed as the sum of acceleration of each factor If the logarithmic growth is to be followed from the end time of the specified time interval to the time when the evaluation time length is added to the end time for the specified evaluation time length, The market situation change according to claim 6, further comprising means for calculating an influence amount of each factor in the situation change with respect to the market share size of the competing factor at each time point from the start time point to the end time point plus the evaluation time length. Analysis equipment. A product, or product category, in a product market that includes a consumer product or system or service where the product itself or a product of the same or similar standard is used repeatedly or continuously by the same individual, or Market conditions that analyze changes in active market conditions where the market share of each competing factor is continually increasing or decreasing when the product provider competes for customer acquisition A change analysis method,
Employer number data storage means for storing time series data of service categories of each competing factor and the number of contracts of the operators,
In the apparatus having the situation vector calculation means and the situation change detection means,
The situation vector calculation means calculates a time series of situation vectors composed of numerical values characterizing the rate of increase or decrease of the market share size of each competing element at each time point of the time series data of the recruitment number data storage means. A situation vector calculation step;
A situation change detecting step in which the situation change detecting means detects a change in the situation vector for a given time interval;
A market situation change analysis method characterized by:

Images