JP2023067836A - Information processing system, information processing method and information processing program - Google Patents

Abstract

To provide an information processing system, an information processing method and an information processing program that easily grasp the degree of contribution, together with the chronological change, of an explanatory variable that does not change with time to the chronological change of an objective variable.SOLUTION: An information processing system 1 includes at least one processor which is capable of executing a program so that each of the following units is carried out. An acquisition unit acquires time series data that changes with the passage of time and non-time series data that doe not change with the passage of time. A calculation unit calculates, on the basis of the acquired time series data, the temporal change of an objective variable that includes non-time series data as an explanatory variable and the contribution of at least some of the explanatory variable to the temporal change of the objective variable. A display processing unit displays in a list form the temporal change of the objective variable and the contribution of the explanatory variable to the temporal change.SELECTED DRAWING: Figure 1

Description

The present invention relates to an information processing system, an information processing method, and an information processing program.

Patent Document 1 discloses a storage unit that stores location information of each of a store and customers, and based on the location information, stores customers who visited the store during a target period during a specific period other than the target period. By specifying the number of revisiting customers who have revisited the store and the number of surviving customers whose whereabouts can be confirmed during a specific period other than the target period among the customers, and calculating the ratio of the revisiting customers among the surviving customers, A data analysis device is disclosed that includes a calculation unit that calculates a customer's continuation rate.

JP 2021-096744 A

In some cases, advanced knowledge of data science for handling time-series data and the like is required in order to investigate the factors of temporal change in objective variables using a data analysis apparatus such as that described in Patent Document 1.

According to one aspect of the invention, an information processing system is provided. This information processing system includes at least one processor capable of executing a program to perform the following steps. The acquisition step acquires time-series data that changes with the passage of time and non-time-series data that does not change with the passage of time. In the calculation step, based on the obtained time-series data, change over time of an objective variable including non-time-series data as an explanatory variable, and contribution of at least part of the explanatory variable to the time-change of the objective variable are calculated. In the display processing step, temporal change of the objective variable and contribution of explanatory variables to the temporal change are displayed in a viewable manner.

According to such a configuration, it is possible to easily grasp the degree of contribution of explanatory variables that do not change in time series to time-series changes in the objective variable as well as time-series changes. Therefore, based on the contribution, it is possible to relax the expertise in data science required when grasping the causal relationship between the objective variable and the explanatory variable.

1 is a configuration diagram showing an information processing system 1; FIG. 2 is a block diagram showing the hardware configuration of the information processing device 2; FIG. 3 is a block diagram showing the hardware configuration of the user terminal 3; FIG. 3 is a diagram illustrating an example of functional units included in the processor 23; FIG. 4 is an activity diagram showing an example of the flow of information processing executed in the information processing system 1; FIG. FIG. 4 is a diagram showing an example of a first image IM1 displayed on a display unit 34; FIG. FIG. 10 is a diagram showing an example of a second image IM2 displayed on the display unit 34;

Embodiments of the present invention will be described below with reference to the drawings. Various features shown in the embodiments shown below can be combined with each other.

By the way, the program for realizing the software appearing in this embodiment may be provided as a non-transitory computer-readable medium (Non-Transitory Computer-Readable Medium), or may be downloaded from an external server. It may be provided as possible, or may be provided so that the program is activated on an external computer and the function is realized on the client terminal (so-called cloud computing).

Further, in the present embodiment, the term “unit” may include, for example, a combination of hardware resources implemented by circuits in a broad sense and software information processing that can be specifically realized by these hardware resources. . In addition, various information is handled in the present embodiment, and these information include, for example, physical values of signal values representing voltage and current, and signal values as binary bit aggregates composed of 0 or 1. Expressed by high and low, or quantum superposition (so-called quantum bits), communication and operations can be performed on circuits in a broad sense.

A circuit in a broad sense is a circuit realized by at least appropriately combining circuits, circuits, processors, memories, and the like. Application Specific Integrated Circuits (ASICs); Programmable Logic Devices (e.g., Simple Programmable Logic Devices (SPLDs); Complex Programmable Logic Devices (CPLDs); and field It includes a programmable gate array (Field Programmable Gate Array: FPGA).

1. Hardware configuration This section describes the hardware configuration.

<Information processing system 1>
FIG. 1 is a configuration diagram showing an information processing system 1. As shown in FIG. The information processing system 1 includes an information processing device 2, a user terminal 3, and a database DB1. The information processing device 2, the user terminal 3, and the database DB1 are configured to be able to communicate with each other through an electric communication line. In one embodiment, information handling system 1 is comprised of one or more devices or components. If, for example, the information processing system 1 consists only of the information processing device 2 , the information processing system 1 can be the information processing device 2 . These constituent elements are described below.

<Database DB1>
The database DB1 stores various information as reference data D0. The reference data D0 is configured so that each component included in the information processing system 1 can be referred to. The reference data D0 may include arbitrary information such as people flow data, map data, traffic information, operation diagrams of public transportation, weather data, purchase data, and transmission data such as blogs and SNS, for example. The reference data D0 can be used as analysis data for analyzing the flow of people at a certain spot.

<Information processing device 2>
FIG. 2 is a block diagram showing the hardware configuration of the information processing device 2. As shown in FIG. The information processing device 2 includes a communication unit 21 , a storage unit 22 , and a processor 23 , and these components are electrically connected inside the information processing device 2 via a communication bus 20 . Each component will be further described.

The communication unit 21 is preferably a wired type communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but wireless LAN network communication, mobile communication such as 3G/LTE/5G, BLUETOOTH (registered trademark) Communication and the like may be included as desired. That is, it is more preferable to implement as a set of these communication means. That is, the information processing device 2 may communicate various information from the outside via the communication unit 21 and the network.

The storage unit 22 stores various information defined by the above description. For example, it can be used as a storage device such as a solid state drive (SSD) for storing various programs related to the information processing device 2 executed by the processor 23, or as a temporary storage device related to program operations. It can be implemented as a memory such as a Random Access Memory (RAM) that stores the necessary information (arguments, arrays, etc.). The storage unit 22 stores various programs, variables, etc. related to the information processing device 2 executed by the processor 23 .

The processor 23 processes and controls overall operations related to the information processing device 2 . The processor 23 is, for example, a central processing unit (CPU) (not shown). The processor 23 implements various functions related to the information processing device 2 by reading a predetermined program stored in the storage unit 22 . That is, information processing by software stored in the storage unit 22 can be specifically realized by the processor 23 which is an example of hardware, and can be executed as each functional unit included in the processor 23 . These are further detailed in the next section. Note that the number of processors 23 is not limited to a single one, and a plurality of processors 23 may be provided for each function. A combination thereof may also be used.

<User terminal 3>
FIG. 3 is a block diagram showing the hardware configuration of the user terminal 3. As shown in FIG. The user terminal 3 includes a communication section 31 , a storage section 32 , a processor 33 , a display section 34 and an input section 35 . It is connected to the. Descriptions of the communication unit 31, the storage unit 32, and the processor 33 are omitted because they are similar to the description of each unit in the information processing device 2. FIG.

The display unit 34 may be included in the housing of the user terminal 3, or may be externally attached. The display unit 34 displays a screen of a graphical user interface (GUI) that can be operated by the user. For example, it is preferable to use a display device such as a CRT display, a liquid crystal display, an organic EL display, and a plasma display according to the type of the user terminal 3 .

The input unit 35 may be included in the housing of the user terminal 3 or may be externally attached. For example, the input unit 35 may be integrated with the display unit 34 and implemented as a touch panel. With a touch panel, the user can input a tap operation, a swipe operation, or the like. Of course, a switch button, a mouse, a QWERTY keyboard, or the like may be employed instead of the touch panel. That is, the input unit 35 receives an operation input made by the user. The input is transferred as a command signal to the processor 33 via the communication bus 30, and the processor 33 can perform predetermined control or calculation as necessary.

2. Functional Configuration of Information Processing Apparatus 2 FIG. 4 is a diagram showing an example of functional units provided in the processor 23 . As shown in FIG. 4 , the processor 23 includes an acquisition section 231 , a generation section 232 , a calculation section 233 and a display processing section 234 .

The acquisition unit 231 is configured to be able to acquire information from the user terminal 3 or other devices. In addition, the acquisition unit 231 reads various information stored in a storage area that is at least a part of the storage unit 22 and writes the read information to a work area that is at least a part of the storage unit 22. , various information can be acquired. A storage area is, for example, an area implemented as a storage device such as an SSD in the storage unit 22 . A working area is, for example, an area implemented as a memory, such as a RAM.

The generation unit 232 is configured to be able to generate various types of information based on the result obtained by the acquisition unit 231 .

The calculation unit 233 is configured to be able to calculate various information based on the acquisition result of the acquisition unit 231, the generation result of the generation unit 232, and the like.

The display processing unit 234 is configured to be able to display various information. The information can be presented to the user via the display 34 of the user terminal 3 or other device. In such a case, for example, the display processing unit 234 controls the display unit 34 of the user terminal 3 to display visual information such as screens, images including still images or moving images, icons, and messages. The display processing unit 234 may generate only rendering information for displaying visual information on the user terminal 3 . Note that the display processing unit 234 may present the output information to the user without going through the user terminal 3 or other device users.

3. Information Processing In this section, information processing executed in the information processing system 1 described above will be described. In this embodiment, the information processing is for analyzing the flow of people to a certain facility. By using the information processing, the user can easily grasp the contribution of the explanatory variable X1 when the flow of people to a certain facility is set as the objective variable Y1. The facility includes commercial facilities such as supermarkets and department stores, entertainment facilities such as karaoke, amusement parks, amusement parks, and sports facilities, lodging facilities such as hotels, vacation rentals, and inns, and transportation facilities such as stations, intersections, airports, and ports. , residential facilities such as offices and residences.

3.1. Flow of Information Processing FIG. 5 is an activity diagram showing an example of the flow of information processing executed in the information processing system 1 . It should be noted that the information processing may include arbitrary exception handling not shown. Exception processing includes interruption of the information processing and omission of each process. The selection or input performed in the information processing may be based on the user's operation, or may be automatically performed without depending on the user's operation.

[Activity A1]
First, the process proceeds to activity A1, and the acquisition unit 231 executes acquisition processing. As a result, the acquisition unit 231 acquires analysis data for obtaining the correlation between the objective variable Y1 and the explanatory variable X1 by referring to the database DB1, by input from the user, or the like. The analytical data may include at least one of structured data, semi-structured data, and unstructured data. Structured data is data standardized to have a predetermined structure. Unstructured data is any form of data that does not have a standardized structure like structured data. Semi-structured data consists of a combination of unstructured data and tags that can identify the unstructured data. Formats of semi-structured data include, for example, graph type, key-value type, document type, and column type. Also, the analysis data may include any form of data such as document data, image data, binary data, and the like. The analysis data may include location information data such as GPS, payment data such as POS data, character data from SNS, search history using any search engine, and the like.

In this embodiment, the explanatory variable X1 includes a finite discrete variable X11 that takes a finite number of discrete values. A finite discrete variable X11 is, for example, a variable representable by integers within the domain defined by the upper and lower bounds. Specifically, the finite discrete variables X11 include explanatory variables X1 represented by finite choices and binary variables such as Boolean variables.

<Time-series data D1, non-time-series data D2>
The acquisition unit 231 of this embodiment acquires the time-series data D1 and the non-time-series data D2. The time-series data D1 is data configured to change over time. The time-series data D1 includes, for example, meteorological data such as weather, temperature, and humidity, purchase data at a certain facility, trend words transmitted at a certain time, and the like. The non-time-series data D2 is data configured so as not to change over time. The time-series data D1 may include at least part of the people flow data D11, which will be described later.

The non-time-series data D2 is not limited to data that does not change at all with the passage of time, and includes data that has a negligibly small amount of change during a predetermined period compared to the time-series data D1. The non-time-series data D2 includes geographic information such as map data, facility layout, facility size, and operation diagrams of public transportation. The non-time-series data D2 may include at least part of the people flow data D11, which will be described later.

<Unstructured data D3>
The acquisition unit 231 of the present embodiment further acquires unstructured data D3 including at least information regarding the holding period of a certain event. The unstructured data D3 is arbitrary, for example, character data, image data, audio data, moving image data, etc. represented by a website, SNS, leaflets, etc. indicating the holding period of the event. Any method can be used to acquire the unstructured data D3. The acquisition unit 231 may acquire, for example, the unstructured data D3 input by the user, or acquire the unstructured data D3 using a predetermined crawling program such as web scraping.

<People flow data D11>
The acquisition unit 231 of the present embodiment further acquires people flow data D11 around a certain spot. A certain spot can be set arbitrarily, but it is, for example, a facility that is the target of analyzing the flow of people. The vicinity of the spot is, for example, an area within a predetermined distance from the facility. The people flow data D11 includes at least temporal changes in the flow of people around the spot as the time-series data D1. The time-series data D1 included in the people flow data D11 includes, for example, the time zone, stay period, movement route, etc. of the people who make up the flow of people visiting the spot. In addition, the people flow data D11 includes attributes of people constituting the people flow as the non-time-series data D2. The attributes include, for example, a person's gender, place of residence, purpose of visiting the area around the spot, and the like.

[Activity A2]
Next, the process proceeds to activity A2, and the generation unit 232 executes the generation process. As a result, the generating unit 232 generates event data D4 indicating the holding period of the event as at least part of the time-series data D1 based on the unstructured data D3 acquired in activity A1. The event data D4 is, for example, the time-series data D1 represented by a Boolean variable that indicates the holding period of the event with 1 and indicates the non-holding period of the event with 0. The event data D4 may include a continuous value indicating the status of the event during the event period. The continuous values are pseudo-continuous values, such as floating point numbers, whose discrete width is negligibly small compared to integers. In this case, the event data D4 generates a continuous value indicating the degree of activity of the event based on the time-series data D1 (for example, the number of posts on SNS, the number of mentions, the number of photos posted, etc.) during the period of the event. . Note that the activity level may be calculated by a calculation process to be described later.

[Activity A3]
Next, the process proceeds to activity A3, and the calculation unit 233 executes calculation processing. As a result, based on the acquired time-series data D1, the calculation unit 233 calculates at least the time change of the objective variable Y1 including the non-time-series data D2 as the explanatory variable X1 and the explanatory variable X1 with respect to the time change of the objective variable Y1. Calculate the partial contribution and When the explanatory variable X1 includes the finite discrete variable X11, the calculation unit 233 calculates the contribution of at least part of the finite discrete variable X11 to the time change of the objective variable Y1 for each discrete value of the finite discrete variable X11. In this embodiment, the calculator 233 further sets the display priority P1 of the explanatory variable X1 based on the calculated contribution. The display priority P1 is an index indicating the degree of influence of the explanatory variable X1 on the objective variable Y1. The display priority P1 may be, for example, the contribution of the explanatory variable X1 to the temporal change of the objective variable Y1. The display priority P1 may be represented, for example, by a statistic of the explanatory variable X1 with respect to the objective variable Y1, such as covariance, correlation coefficient, and the like. By such calculation processing, the calculation unit 233 selects the explanatory variable corresponding to the objective variable Y1 for each explanatory variable X1 out of at least one explanatory variable X1 that is a variation factor of various people flows contained in the people flow data D11. X1 is identified and the contribution of the explanatory variable X1 to the time change of the objective variable Y1 is calculated. For example, the calculation method can employ any statistical method such as TF-IDF (term frequency-inverse document frequency) method, Granger causality test, DID (difference of differences method).

[Activity A4]
Next, the process proceeds to activity A4, and the display processing unit 234 executes display processing. Thereby, the display processing unit 234 causes the display unit 34 to display the temporal change of the objective variable Y1 and the contribution of the explanatory variable X1 to the temporal change in a viewable manner. When the explanatory variable X1 includes the finite discrete variable X11, the display processing unit 234 displays the time change of the objective variable Y1, the contribution of the discrete value to the time change, and the finite discrete variable X11 in a viewable manner. Further, in the present embodiment, the display processing unit 234 preferentially displays the explanatory variable X1 with the high display priority P1.

3.2. Example of Image Displayed as a Result of Information Processing This section describes an example of an image displayed on the display unit 34 as a result of the above information processing (especially the display processing of activity A4).
3.2.1. About the first image IM1

<First image IM1>
FIG. 6 is a diagram showing an example of the first image IM1 displayed on the display unit 34. As shown in FIG. The first image IM1 is an image for displaying the temporal change of the objective variable Y1 and the contribution of the explanatory variable X1 to the temporal change in a viewable manner. The objective variable Y1 in this embodiment is the flow of people around a certain facility. That is, the above information processing is used for analysis of people flow. The first image IM1 includes a first temporal change display area 4 and a first explanatory variable display area 5. FIG. In this embodiment, all the first explanatory variable display areas 5 are arranged in substantially the same direction from the first time-varying display area 4 . Specifically, all the first explanatory variable display areas 5 are displayed on the right side of the first time-varying display area 4 . In other words, the first time-varying display area 4 is displayed in the end area of the display section 34 . Specifically, the first time-varying display area 4 is displayed at the left end of the display section 34 . This makes it easier for the user to visually distinguish between the area showing information about the objective variable Y1 and the area showing information about the explanatory variable X1. The display modes of the first time change display area 4 and the first explanatory variable display area 5 are arbitrary.

<First time change display area 4>
The first temporal change display area 4 is an area showing the temporal change of the objective variable Y1. The first time-varying display area 4 includes one variable name display area 41 and at least one (five in this embodiment) time-varying display areas 42 .

<Variable name display area 41>
The variable name display area 41 displays the variable name of the objective variable Y1 (“people flow” in this embodiment).

<Time change display area 42>
Each time change display area 42 displays changes in the flow of people for a certain period of time. In the present embodiment, the time change display area 42 displays how much the flow of people at the reference date and time for analysis has changed compared to the comparison period before the reference date and time. For example, the time change display area 42 shows changes in the flow of people from the previous day, from the previous week, from the previous month, and during a predetermined period (August 12, 2020 to August 18, 2020) at the reference date and time. Note that the reference date and time can be changed as appropriate according to the comparison period to be compared. For example, when comparing day-to-day changes, the reference date and time may be the total flow of people for one day. Such changes in the flow of people are displayed as numerical values at arbitrary positions included in the time-varying display area 42, for example. In the present embodiment, changes in the flow of people are displayed in the time-varying display area 42 as an increase/decrease rate in a form that can be listed with the comparison target period corresponding to the time-varying display area 42 . In addition, at least one of the time-change display areas 42 is configured to be able to display a comparison result in an arbitrary comparison target period in the time-change display area 42 according to user's operation.

<First explanatory variable display area 5>
Each of the first explanatory variable display areas 5 is an area showing the contribution of the explanatory variable X1 to the temporal change of the objective variable Y1. Each of the first explanatory variable display areas 5 includes one variable name display area 51 and at least one first contribution display area 52 .

<Variable name display area 51>
The variable name display area 51 displays the variable names of the explanatory variable X1 ("word", "place of residence", and "time zone" in this embodiment). Of these, "words" can include any trend word, and therefore can be defined by an almost infinite number of integers when defined by any trend word. In addition, when a "word" is composed of a predetermined finite number of trend words, it can be said that the "word" belongs to the finite discrete variable X11. On the other hand, "place of residence" belongs to the finite discrete variable X11 because it is a subset of a finite and discrete set represented by administrative divisions and the like. On the other hand, the "time zone" may be configured to belong to a substantially continuous value, or may be configured to belong to the finite discrete variable X11 by dividing it by a predetermined finite time zone.

<First contribution display area 52>
The contribution of each explanatory variable X1 to the time change of the objective variable Y1 is displayed in the first contribution display area 52 . Specifically, the contribution of each possible value of the explanatory variable X1 to the time change of the objective variable Y1 is displayed in the first contribution display area 52 . For example, in the first contribution display area 52 corresponding to "word", trend words ("XX fireworks display", "XX center building", "sale", " XX park") is displayed to the time change of the objective variable Y1. In the first contribution display area 52 corresponding to "place of residence", places of residence ("Chiyoda Ward", "Setagaya Ward", "Shibuya Ward", "Meguro , etc.) to the time change of the objective variable Y1 is displayed. In the first contribution display area 52 corresponding to "time zone", the contribution to the time change of the objective variable Y1 for each time zone (4 hours in this embodiment) is displayed. In particular, the number of possible values of the explanatory variable X1 corresponding to “word” is greater than the number displayed in the first contribution display area 52 . Therefore, the first contribution display area 52 preferentially displays the value of the explanatory variable X1 with the high display priority P1 (for example, contribution). Therefore, the first contribution display area 52 is configured such that the value of the explanatory variable X1 to be displayed can be set by the user. For example, the first contribution display area 52 is configured to be able to increase the display number of possible values of the explanatory variable X1, or is configured to be able to change the displayed value of the explanatory variable X1.

Note that the explanatory variable X1 is not limited to those displayed in FIG. 6, and may include other explanatory variables X1. However, there is an upper limit to the number of explanatory variables X1 that can be displayed in the first image IM1 due to restrictions on the display unit 34 and the like. Therefore, the display processing unit 234 preferentially displays the explanatory variable X1 with a high display priority P1 (for example, the explanatory variable X1 with a large contribution) among the explanatory variables X1 calculated in the activity A2. This facilitates analysis of the time-series data D1.

3.2.2. Second Image IM2 In this section, a second image IM2, which is another example of an image displayed on the display unit 34 as a result of the above information processing, will be described.

<Second image IM2>
FIG. 7 is a diagram showing an example of the second image IM2 displayed on the display unit 34. As shown in FIG. The second image IM2, like the first image IM1, is an image for displaying the temporal change of the objective variable Y1 and the contribution of the explanatory variable X1 to the temporal change in a viewable manner. In particular, the second image IM2 is an image for analyzing the contribution of one of the multiple explanatory variables X1 to the time change of the people flow data D11. The second image IM2 of the present embodiment analyzes the contribution of one value "XX fireworks display" of "word", which is one of the explanatory variables X1, to the time change of the people flow data D11 as the objective variable Y1. It is an image for For example, when the first contribution display area 52 corresponding to the value of the specific explanatory variable X1 is specified in the first image IM1, the display processing unit 234 displays the second image IM2 corresponding to the value. Processing is performed so as to be displayed on the unit 34 . For example, the display processing unit 234 may cause the display unit 34 to display the first image IM1 and the second image IM2 in such a manner that they can transition to each other.

The second image IM2 includes a second time-varying display area 6, a second explanatory variable display area 7, and a second contribution display area 8. FIG.

<Second time change display area 6>
The second time change display area 6 is configured so that the time change of the objective variable Y1 can be visually grasped. In this embodiment, the people flow data D11, which is the objective variable Y1, is configured so as to be able to grasp the temporal change for each day. Specifically, the second time-varying display area 6 is displayed by a line graph with the date on the horizontal axis and the flow of people (for example, the number of visitors) on the vertical axis. The vertical axis and horizontal axis can be arbitrarily set by the user. For example, the vertical axis may be the contribution of one day of "XX Fireworks Festival", which is one of the possible values of the explanatory variable X1. The explanatory variable X1 displayed in the second time-varying display area 6 and its value can be set by the user. In addition, the period of time change displayed in the second time change display area 6 can also be set by the user. Moreover, the display mode of the second time-change display area 6 is not limited to a line graph, and may be a bar graph, a circle graph, a radar chart, table data, or the like.

<Second explanatory variable display area 7>
The second explanatory variable display area 7 is configured to display information about the value of the explanatory variable X1 displayed in the second time-varying display area 6 . The information is extracted, for example, from the time-series data D1 and the non-time-series data D2 acquired in activity A1. Also, the information may be extracted from event data D4 generated in activity A2. In this embodiment, in the second explanatory variable display area 7, the value of the explanatory variable X1 set in the second time change display area 6 (in this embodiment, "XX fireworks Various information about the competition") is displayed. For example, in the second explanatory variable display area 7, the contribution of "XX Fireworks Festival" during a predetermined period (in this embodiment, from August 12, 2020 to August 16, 2020), The total number of visitors, the holding period, the holding place (XX station west area), the holding facility (XX park), etc. are displayed. The second explanatory variable display area 7 may be configured such that the information can be changed as appropriate by the user.

<Second contribution display area 8>
The second contribution display area 8 displays information about the contribution of the value of a certain explanatory variable X1. For example, in the second contribution display area 8, a statistical value of information that is the basis for the contribution of a certain explanatory variable X1 value ("XX fireworks display" in this embodiment), at least part of the information itself, etc. display. Hereinafter, for convenience of explanation, the information that serves as the basis for the contribution of the value of a certain explanatory variable X1 among the analysis data may be referred to as "basis information". In this embodiment, the second contribution display area 8 includes first visual information 81 , second visual information 82 and third visual information 83 .

<First visual information 81>
The first visual information 81 is configured to allow visually grasping of the information regarding the classification of ground information belonging to "XX fireworks display" among the acquired analysis data. Specifically, the first visual information 81 is configured so that the classification of the evaluation for "XX fireworks display" can be visually grasped. In this embodiment, the classification of evaluation includes "positive" which is favorable evaluation and "negative" which is negative evaluation. The calculation unit 233 performs predetermined calculation processing such as natural language processing, statistical processing, and machine learning processing on the analysis data, and assigns these evaluation classifications to various basis information included in the analysis data. . Examples of such classification methods include processing applied to classification problems (eg, principal component analysis, k-means method, etc.). The first visual information 81 of this embodiment is composed of a pie chart. In the center of the pie chart, the classification name of the evaluation classification having the highest percentage among the total ("positive" in this embodiment) and its numerical value are displayed.

<Second visual information 82>
The second visual information 82 is configured so that statistical information relating to each piece of basis information belonging to "XX fireworks display" among the acquired analysis data can be visually grasped. Here, a case where the basis information contains character data will be described, but the same can be applied to cases where the basis information contains numerical data or image data. The second visual information 82 displays statistical information about character strings that serve as a basis for determining that the relevant basis information belongs to "XX Fireworks Festival" among the character data included in each of the relevant basis information. For example, the second visual information 82 includes character strings such as "fireworks", "beautiful", "delicious", and "summer memories" among the basis information included in the holding period of the XX fireworks festival. The number of base information including keywords (in other words, frequently occurring words) is displayed as visual information. In this embodiment, the second visual information 82 is configured to display, for each keyword, the number of basis information containing the keyword as a bar graph. Note that the specific aspect of the second visual information 82 is not limited to this. The second visual information 82 and the first visual information 81 are configured so as to be viewable in the vertical direction. Specifically, the second visual information 82 is displayed below the first visual information 81 .

<Third visual information 83>
The third visual information 83 is configured so that information relating to ground information can be visually recognized. The third visual information 83 includes an attribute display area 831 and a basis information display area 832 .

<Attribute display area 831>
The attribute display area 831 is configured so that the classification of ground information ("positive" and "negative" in this embodiment) can be specified. The display processing unit 234 changes the display contents of the ground information display area 832 described later according to the user's operation on the attribute display area 831 .

<Basis Information Display Area 832>
The basis information display area 832 is configured to be able to display basis information for each classification of basis information ("positive" and "negative" in this embodiment). In this embodiment, the basis information display area 832 is configured so that the content of the basis information (for example, SNS posts, blog articles, etc.) can be visually recognized for each classification of the basis information. The display processing unit 234 may display the basis information displayed in the basis information display area 832 in a manner different from other character strings for the keyword displayed in the second visual information 82 . In other words, the display processing unit 234 may highlight and display the keyword displayed in the second visual information 82 in the basis information displayed in the basis information display area 832 . This makes it easier for the user to analyze the basis information.

4. Others The aspect of the information processing described above is merely an example, and is not limited to this.

The display processing unit 234 may display the first image IM1 and the second image IM2 in any manner. For example, the display processing unit 234 may display the first image IM1 and the second image IM2 in a viewable manner. When the designation of the region 52 is input, the details of the contribution of the value of the explanatory variable X1 corresponding to the first contribution display region 52 are superimposed on the first image IM1 as the second image IM2. You may let

Further, the display processing unit 234 may independently display the first image IM1 and the second image IM2 on at least one display unit 34 . Moreover, the display processing unit 234 may display only one of the first image IM1 and the second image IM2.

The information processing device 2 may be in an on-premise form or in a cloud form. The cloud-type information processing apparatus 2 may provide the above functions and processes in the form of, for example, SaaS (Software as a Service) or cloud computing.

In the above embodiment, the information processing device 2 performs various types of storage and control, but instead of the information processing device 2, a plurality of external devices may be used. That is, various information and programs may be distributed and stored in a plurality of external devices using blockchain technology or the like.

The aspect of the above embodiment is not limited to the information processing system 1, and may be an information processing method or an information processing program. The information processing method includes each step of the information processing system 1 . The information processing program causes at least one computer to execute each step of the information processing system 1 .

The information processing system 1 and the like may be provided in the following modes.

(1) An information processing system, comprising at least one processor capable of executing a program so as to perform the following steps, and in the obtaining step, time-series data that changes over time, non-time-series data that does not change, and in a calculation step, based on the acquired time-series data, the time change of an objective variable containing the non-time-series data as an explanatory variable, and the time change of the objective variable contribution of at least a part of the explanatory variable, and, in a display processing step, the time change of the objective variable and the contribution of the explanatory variable to the time change are displayed in a viewable manner.

According to such a configuration, it is possible to easily grasp the degree of contribution of explanatory variables that do not change in time series to time-series changes in the objective variable as well as time-series changes. Therefore, based on the contribution, it is possible to relax the expertise in data science required when grasping the causal relationship between the objective variable and the explanatory variable.

(2) In the information processing system described in (1) above, the acquiring step acquires unstructured data including at least information about the holding period of a certain event, and the generating step acquires the acquired unstructured data. to generate event data, which is time-series data indicating the holding period of the event, based on

According to such a configuration, it is possible to process the information included in the text data as time-series data, so that the contribution of the objective variable to the temporal change can be calculated with higher accuracy.

(3) In the information processing system described in (2) above, the event data includes a continuous value indicating the holding status of the event during the holding period.

According to such a configuration, it is possible to reflect the holding status of the event in the time-series analysis, so it is possible to further improve the convenience.

(4) In the information processing system according to any one of (1) to (3) above, the obtaining step further obtains people flow data around a certain spot, and the people flow data is the time-series data. The data includes at least temporal changes in the flow of people around the spot, and the non-time-series data includes the attributes of the people who make up the flow of people.

According to such a configuration, it is possible to improve convenience in market analysis.

(5) In the information processing system according to any one of (1) to (4) above, the explanatory variable includes a finite discrete variable that takes a finite number of discrete values, and in the calculating step, the objective calculating the contribution of at least a portion of the finite discrete variable to the time variation of the variable for each discrete value of the finite discrete variable; and displayed in an overviewable manner for each of said finite discrete variables.

According to such a configuration, it becomes easy to grasp the contribution of the finite discrete variable to the time change of the objective variable for each discrete value. Therefore, it becomes easier to grasp the contribution of the explanatory variables to the temporal change of the objective variable in more detail.

(6) In the information processing system according to any one of (1) to (5) above, in the display processing step, the display priority of the explanatory variable is set based on the calculated contribution, and the display Preferentially displaying the explanatory variables with high priority.

According to such a configuration, since explanatory variables with large contributions are preferentially displayed, analysis of time-series data is facilitated.

(7) An information processing method, comprising steps of the information processing system according to any one of (1) to (6) above.

(8) An information processing program that causes at least one computer to execute each step of the information processing system according to any one of (1) to (6) above.
Of course, this is not the only case.

Furthermore, the following points should also be noted.

For example, when local governments, developers, shopping associations, etc. plan new facility construction, event holding, etc., they make future predictions by referring to past people flow information.

However, until now, it has been difficult to efficiently analyze and predict the flow of people and economic effects due to events by analyzing a large amount of information including information on the flow of people in the past.

In view of the problems of the prior art, an object of the present invention is to enable efficient analysis and prediction of the flow of people and the economic effect of an event by analyzing a large amount of bustle information including information on the flow of people. .

In order to solve the above-described problems, a program according to a first aspect of the present invention provides a computer related to an information processing system that extracts a specific point, a specific district, or a specific area that is partitioned two-dimensionally or three-dimensionally. a specific area definition unit that defines a specific area where the a crowd state information collection unit for collecting crowd state information including information on the flow of people and information on factors affecting the flow of people; a specific analysis unit that performs a specific analysis based on second information on the flow of people at a second point in time or a second period of time regarding the and a fluctuation information presenting unit that presents the fluctuation information of the busy state in order to visualize the factors affecting the

According to the first aspect of the present invention, it is possible to efficiently analyze and predict the flow of people and the economic effect of an event by analyzing a large amount of bustle information including information on the flow of people.

The 'specific area' is a part of the 'specific point, specific district, or specific area' and is an area subject to evaluation of the state of activity.

“Two-dimensionally or three-dimensionally partitioned” is defined by the information processing system itself from “a specific point, a specific district, or a specific area” or is defined by an input by the user of the information processing system.

The "bustling state" includes the state of the flow of people and the states of factors that influence the state of the flow of people, and includes, for example, the states of "bustling" and "crowded."

"People flow information" includes, for example, information about the number of people present at a specific location (point, district, or region) at a specific time or period. It may also contain information about the number of human movements.

"Specific analysis" refers to analysis for visualizing the causal relationship between temporal changes in the flow of people and the factors that affect the temporal changes in the flow of people. .

“Fluctuation information” is information indicating temporal fluctuations.

The operation of defining the specific area performed by the specific area definition unit and the operation of defining the bustling state variable performed by the bustle state variable definition unit may be operations in which the computer takes in data therein according to user input. .

"Information on factors that affect the flow of people" includes emotional information (including personal information such as so-called "tweet" information on SNS and search word information on search sites), payment information (including so-called POS data), At least one of them may be included.
The specific analysis may be an analysis using a difference difference method that takes a difference between a first fluctuation in the flow of people caused by a first factor and a second fluctuation in the flow of people caused by a second factor similar to the first factor. .

The first factor and the second factor are events similar to each other, events such as seasons, weather, infectious diseases, or events with cycles such as every day, every week, every month, every year It may be due to

The information processing system includes a recording unit capable of recording information including the people flow information, and at least one of the first people flow information and the second people flow information is read from the recording unit and sent to the specific analysis unit. It may be input.

The specific area definition unit defines at least a first specific area and a second specific area, and the specific analysis unit performs a first specific area at a first point in time or a first time period with respect to the first specific area. 1 people flow information, 1st specific area 2nd people flow information at a 2nd time point or a 2nd period regarding a 1st specific area, 2nd people flow information at a 1st time point or a 1st period regarding said 2nd specific area The specific analysis is performed from the specific area first people flow information and the second specific area second people flow information at the second point in time or in the second period regarding the second specific area, and the fluctuation information is obtained from the first people flow information It may include two-dimensional or three-dimensional directional information between the specific area and the second specific area.

A recording medium according to a second aspect of the present invention is a recording medium storing the program according to the first aspect.

An information processing system according to a third aspect of the present invention includes a specific area definition unit that defines a specific area from which a specific point, a specific district, or a specific area is divided two-dimensionally or three-dimensionally and extracted; A bustling state definition unit that defines a bustling state indicating a bustling state including a flow of people at a point or the specific district or the specific area; A bustling state information collecting unit for collecting state information, first information on the flow of people at a first point in time or in a first period regarding the specific area, and second flow of people at a second point in time or in a second period regarding the specific area a specific analysis unit that performs a specific analysis based on information; and based on the specific analysis result by the specific analysis unit and information on the factors that affect the flow of people, fluctuations in the crowding state in order to visualize the factors that affect the flow of people. and a fluctuation information presentation unit that presents information.

In an information processing method according to a fourth aspect of the present invention, a computer according to an information processing system defines a specific area from which a specific point, a specific district, or a specific area is divided two-dimensionally or three-dimensionally and extracted. a step of defining a specific area; a step of defining a bustle state indicating a state related to the flow of people in the specific point or the specific district or the specific area; a crowd state information collection step of collecting crowd state information including information on influencing factors; a specific analysis step of performing a specific analysis from the second people flow information in the period 2, and visualizing the factors affecting the people flow based on the specific analysis result of the specific analysis step and the information of the factors affecting the people flow. and a fluctuation information presenting step of presenting the fluctuation information of the busy state.

According to the present invention, it is possible to efficiently analyze and predict the flow of people and the economic effect of an event by analyzing a large amount of bustle information including information on the flow of people.

<Solution Overview>
Three features that realize data-driven area management

1. Data related to areas with high utilization hurdles can be used without specialized knowledge Data useful for grasping the bustle of an area include people flow data (GPS), IoT data (cameras, etc.), purchase data, SNS data, POI data, etc. There are many, but it is difficult to collect and store them in-house, and advanced technology is required to combine and analyze data in different formats. Based on the knowledge of our company, which develops a wide range of data analysis services, this service is designed so that even people without knowledge of data utilization can intuitively operate and obtain the necessary information.

2. With quasi-real-time data and advanced analysis technology, it is possible to visualize KPIs unique to each company. was considered difficult.

By utilizing quasi-real-time data on the flow of people in 15-minute increments, this service does not miss detailed changes in areas such as "I want to know the status of rush hours on weekdays." We also listen to the customer's area-specific KPI and provide a monitoring environment tailored to the customer based on our data analysis technology. We support the realization of “ideal city development”.

3. Visualizing "bustle" and unraveling causal relationships from external data "bustle" is one of the most important indicators in area management.

This service displays the status of people flow and excursion, which is an important element of "bustle", on a map, and it is possible to compare time series (area / time period) using graphs. In addition, for points of concern about changes, an insight analysis function that utilizes SNS data is used to link changes in the flow of people with trend words on SNS. It is possible to "estimate the effect of the event" by displaying "to what extent / in what context the measure became a topic".

INDUSTRIAL APPLICABILITY According to each aspect of the present invention, it is possible to efficiently analyze and predict the flow of people and the economic effect of an event by analyzing bustle information.

Furthermore, the following points should also be noted.

In the restaurant service industry, where it is said that "location determines 70% of victory or defeat", in many cases, business owners select locations based on local familiarity and experience. On the other hand, real estate owners and landlords have few criteria for judging the location value according to the type of business, and they demand rents above (or below) the market price. This causes results such as "I thought I chose a good location, but there are few customers" and "I thought I had rented it to a good business owner, but it went bankrupt," resulting in a high business failure rate (probability of failure) of 6.4%. there is

When opening a new store in a restaurant, it is very important where to open the store.
However, the current situation is that it is difficult to find a point that lowers the probability of failure, or that there is no optimal tool.

In Japanese Patent No. 4728229, as a customer behavior analysis for identifying the cause of the sales and accompanying sales from the purchase history of the product, the location information and time information of the customer in the store are acquired, and the space in the store is analyzed. In addition, based on the acquired position information, time information, and space information, route information indicating the customer's movement route in the space in the store by the position in the virtual space is generated based on the location information and time information, and the customer's purchasing behavior is determined by the pattern determination unit based on the behavior pattern data, route information, and speed information, which are the types of purchasing behavior. A technical idea is disclosed for determining which of the types of , and outputting the result of the determination.

Originally, we should be blessed with opportunities to seize business opportunities by conducting hypothesis verification based on data for hypotheses generated in business activities, but the current situation is that "data cannot be fully used" due to various barriers. There is

In the face of diversifying customer needs, corporate activities are becoming more and more complicated, and we are thinking about what kind of products we should develop and what kind of marketing we should do in order to increase our company's operating income. Therefore, detailed data analysis is an essential issue. However, advanced companies that want to try data analysis do not have such a big data analysis infrastructure, data collection and processing to improve analysis accuracy do not go well, data analysis, algorithm experts (data scientists) Inability to access the site, operation, system construction/service development, etc. are not going well.

In view of these problems in the prior art, the present invention estimates sales simply by inputting the type of store to be opened and candidate locations, and supports and solves store opening strategies that reduce the probability of failure. An object of the present invention is to provide a system, a method, a program, and a recording medium storing the program.

In order to solve the above problems, an information system according to a first aspect of the present invention is a system for searching for the best store opening location, and includes an input unit for inputting a store opening location and business type information, a display unit for displaying information on competing stores in a variable area including the store opening location when the store opening location and the business type information are input to the input unit; An estimation unit for estimating sales in the case of opening a store at the store opening point from information on the flow of people and/or congestion, and an analysis for analyzing the return on investment when the store is opened at the store opening point based on the data estimated by the estimation unit. It is characterized by comprising a part.

As the information system according to the second aspect of the present invention, in the first aspect, the estimation unit may use machine learning.

As an information system according to a third aspect of the present invention, in the second aspect, the machine learning may be learning using a learned geospatial prediction model.

As an information system according to a fourth aspect of the present invention, in the first aspect, the estimation unit may process big data, be processed in real time, and perform estimation by machine learning.

As an information system according to a fifth aspect of the present invention, in the first aspect, the information system may further include means for narrowing down store opening locations based on at least one of GPS data, people flow data, population data, and annual household income data.

In order to solve the above-described problems, an information processing method according to a sixth aspect of the present invention provides a button displayed on a landing page on the Web, and when the button is clicked, a At least one of restaurant category, target demographic, area and/or nearest station, store size and/or number of seats, according to the scenario linked to the button selected from the two buttons of store opening survey and competition comparison. A keyword associated with one of them is input, a map of the area is displayed, the flow of people and competing stores are displayed on the map, a candidate location for opening a store is clicked in the area, and a candidate location for opening a store is displayed in the area. When is clicked, the keyword is collated with various databases, necessary data is extracted from the database, data analysis is performed by optimal visualization based on the data characteristics of the extracted data, and estimated sales of the store information, information on the number of competing stores in the vicinity, information on the flow of people, data obtained from business operations and/or activities and/or information on graphs. It is characterized by analyzing and outputting the result of applying to the template wording.

In order to solve the above problems, a program according to a seventh aspect of the present invention provides a computer with first means for separating a keyword from an input sentence, second means for collating the keyword with various databases, A third means for extracting necessary data from the database, a fourth means for enabling data analysis by optimal visualization based on the data characteristics of the extracted data, estimated sales, and neighborhood competition. It is characterized by functioning as a fifth means for collecting, storing, and analyzing data and/or graph information obtained from the number of stores, the flow of people, business operations and activities, and outputting the results of applying them to template wording. do.

As the eighth aspect, the program according to the seventh aspect can be realized as a recording medium storing the program.

According to each aspect of the present invention, it is possible to realize an information system that is close to the user and provides a platform for delivering the user's "wants" (information, things).

An embodiment of the present invention finds the best place to open a store by estimating the sales if the store opens at that location from information on competing stores on the Web and information on the flow of people and congestion.

An embodiment of the present invention can look for the best store locations derived from data. From information on existing stores, it is also possible to estimate sales information when a store is opened at that location.

One embodiment of the present invention has a mechanism in which past store sales are input, and since re-learning is performed, sales accuracy becomes higher.

One embodiment of the present invention realizes a more accurate sales estimation model by AI represented by machine learning.

One embodiment of the present invention features machine learning sales estimation and reinforcement learning.

One embodiment of the invention features a trained geospatial prediction model.

One embodiment of the present invention implements a sales estimation model through big data processing, real-time processing, and machine learning.

An embodiment of the present invention utilizes external data (GPS data, people flow data, population data, annual household income data, etc.) to narrow down candidate locations for store openings and achieve sales forecasting by AI.

One embodiment of the present invention is characterized by reducing the failure rate of store opening plans by estimating sales.

One embodiment of the present invention is characterized by reducing the failure rate of store opening plans with AI support.

One embodiment of the present invention is mobile spatial data linked to a variable mesh (area) from 250m to 1000m by birth/age/time, location information linked to movement route/stay time/number of visits, facilities/roads. /Use the number of people getting on and off at stations linked to tracks/parking, and open statistical data linked to population/households/business establishments/annual income/consumption as input for AI, and output estimated values for store sales, property prices, and area potential. It is characterized by

An embodiment of the present invention is implemented by combining machine learning with a system (geographic information system) that performs processing such as association with various geographical information and visually displays it on a data-based map.

One embodiment of the present invention is characterized by a system that performs processing such as associating newly updated fresh data with various geographical information and visually displaying it on a digitized map.

One embodiment of the present invention includes a visualization function for narrowing down candidate locations for opening a store, a heat map display of the population and flow of people (demographic distribution) of nearby stores, visualization of the trade area range of own store and competing stores, and・Realize the visualization of the time-series flow of people at competing stores and sales forecasting by AI at candidate locations for store openings.

An embodiment of the present invention is applicable to restaurants that are considering opening new restaurants and restaurant companies that have small to medium-sized affiliated restaurants that already operate 1-20 restaurants.

An embodiment of the present invention is applicable to food and beverage consulting.

An embodiment of the present invention is applicable to store opening planning, existing store development, customer analysis, investment decisions, and sales/leasing management.

One embodiment of the present invention uses CVR (conversion rate) from Landing page as Key Metrics.

One embodiment of the present invention uses CVR (conversion rate) to paying members as the Key Metrics.

One embodiment of the present invention uses retention rate as the Key Metrics.

One embodiment of the present invention uses data entry rate as the Key Metrics.

One embodiment of the present invention uses Web Landing page, МaiL magazine as an electronic publishing platform that provides users with the ability to post and view articles including text, images, videos, etc. as Channels functions as Opened Magazine. and collaborate with famous restaurant-related website companies and restaurants.

One embodiment of the present invention does not require code entry with AI as an assistant function, and provides analysis on pre-made screens and data acquisition by interactive input and personalized recommendation mechanism. There is no need to type SQL queries that require specialized knowledge, and a series of data utilization processes can be efficiently performed, from data acquisition to analysis, insight reading, and business action consideration.

One embodiment of the present invention enables an AI assistant to instantaneously receive optimal graph information and insights based on Japanese keywords entered by a user.

In one embodiment of the present invention, the user does not need to attend dozens of hours of training on how to use the tool in advance to acquire specialized skills, nor does it need to construct a screen in advance, and the data can be utilized. will be able to do by themselves.

One embodiment of the present invention enables anyone to easily understand hypothesis verification by an AI assistant based on the characteristics of data. Each person can do their own data analysis.

According to each aspect of the present invention, it is possible to develop a system for extracting data for estimating sales after opening a store, whether it is the situation of competitors opening stores, whether the flow of people matches the rent, or whether the flow of people matches the customer model of the company. becomes possible.

Therefore, the present invention has wide applicability in related industries.

Finally, while various embodiments of the present disclosure have been described, they have been presented by way of example and are not intended to limit the scope of the invention. The novel embodiment can be embodied in various other forms, and various omissions, replacements, and modifications can be made without departing from the scope of the invention. The embodiment and its modifications are included in the scope and gist of the invention, and are included in the scope of the invention described in the claims and equivalents thereof.

1: information processing system 2: information processing device 20: communication bus 21: communication unit 22: storage unit 23: processor 231: acquisition unit 232: generation unit 233: calculation unit 234: display processing unit 3: user terminal 30: communication bus 31 : Communication unit 32 : Storage unit 33 : Processor 34 : Display unit 35 : Input unit 4 : First time change display area 41 : Variable name display area 42 : Time change display area 5 : First explanatory variable display area 51 : Variable name display area 52 : First contribution display area 6 : Second time change display area 7 : Second explanatory variable display area 8 : Second contribution display area 81 : First visual information 82 : Second visual information 83 : third visual information 831 : attribute display area 832 : basis information display area DB1 : database IM1 : first image IM2 : second image

Claims (8)

An information processing system,
at least one processor operable to execute a program such that the following steps are performed;
The acquisition step acquires time-series data that changes with the passage of time and non-time-series data that does not change with the passage of time,
In the calculation step, based on the acquired time-series data, temporal change of an objective variable including the non-time-series data as an explanatory variable, and contribution of at least part of the explanatory variable to the temporal change of the objective variable. calculate,
In the display processing step, the temporal change of the objective variable and the contribution of the explanatory variable to the temporal change are displayed in a viewable manner. In the information processing system according to claim 1,
The obtaining step obtains unstructured data including information about the duration of at least an event;
In the generating step, event data, which is chronological data indicating a holding period of the event, is generated based on the acquired unstructured data. In the information processing system according to claim 2,
The event data includes a continuous value indicating the holding status of the event during the holding period. In the information processing system according to claim 1,
The obtaining step further obtains people flow data around a certain spot,
The people flow data includes at least temporal changes in the flow of people around the spot as the time-series data, and includes attributes of people constituting the flow of people as the non-time-series data. In the information processing system according to claim 1,
the explanatory variable comprises a finite discrete variable that takes a finite number of discrete values;
In the calculating step, the contribution of at least a portion of the finite discrete variable to the time variation of the objective variable is calculated for each discrete value of the finite discrete variable;
In the display processing step, the time change of the objective variable, the contribution of the discrete value to the time change, and the finite discrete variable are displayed in a viewable manner. In the information processing system according to claim 1,
In the display processing step, the display priority of the explanatory variables is set based on the calculated contribution,
The explanatory variable having the higher display priority is preferentially displayed. An information processing method,
A method comprising the steps of an information processing system according to any one of claims 1-6. An information processing program,
A computer that causes at least one computer to execute each step of the information processing system according to any one of claims 1 to 6.

Images