JP7378696B1 - Questionnaire analysis method, questionnaire analysis device and program - Google Patents

Abstract

[Problem] To provide a questionnaire analysis method, a questionnaire analysis device, and a program that can realize questionnaire analysis based on responses from a wide range of survey subjects regardless of the presence or absence of a terminal. [Solution] The questionnaire analysis method includes a communication step of acquiring, through communication, first questionnaire information indicating the contents of the questionnaire input through a web page displayed on a terminal 5 of a questionnaire subject who has read an identification code 115; an input step for receiving input of second questionnaire information obtained by converting the questionnaire contents written by hand or print on a postcard 110 (submission) submitted by a person into data format, and each of the first questionnaire information and the second questionnaire information. an analysis step of analyzing the contents of the questionnaire and performing an analysis process of assigning a classification according to the contents. [Selection diagram] Figure 1

Description

The present disclosure relates to a questionnaire analysis method, a questionnaire analysis device, and a program.

2. Description of the Related Art Conventionally, there has been known a technique for obtaining questionnaire responses from questionnaire subjects using an identification code such as a QR code (registered trademark). For example, Patent Document 1 describes this type of technology. Patent Document 1 describes that a recipient side terminal accesses a web server using a two-dimensional barcode of a posted distribution, and a link means to a questionnaire means is displayed on a display screen.

JP2013-246800

By writing an identification code on the distributed material as in the prior art, it is possible to efficiently obtain answers from questionnaire subjects who have terminals. However, it is not possible to obtain responses from survey respondents who do not own a terminal or who are unfamiliar with operating a terminal. There is room for improvement in the conventional technology when it is desired to obtain as many responses as possible from survey subjects or when it is necessary to obtain responses from survey subjects who do not own a terminal.

An object of the present disclosure is to provide a questionnaire analysis method, a questionnaire analysis device, and a program that can realize questionnaire analysis based on responses from a wide range of survey subjects regardless of whether they have a terminal or not.

One aspect of the present invention includes a communication step of acquiring, through communication, first questionnaire information indicating the questionnaire contents input through a web page displayed on a terminal of a questionnaire subject who has read an identification code; an input step of accepting input of second questionnaire information obtained by converting the questionnaire contents written in handwriting or printing on the submission into a data format; and analyzing the questionnaire contents of each of the first questionnaire information and the second questionnaire information. and an analysis step of performing analysis processing to assign classifications according to content.

In the analysis step, the analysis process may be performed based on a learning model that has been subjected to a learning process based on a data set in which the questionnaire content is input information and the classification corresponding to the questionnaire content is output information.

The questionnaire contents inputted through the web page may be in a free entry format, and the field for writing or printing the questionnaire contents in the submission may be in a free entry format.

The method further includes an integrating step of performing an integrating process of integrating data, among the first questionnaire information and the second questionnaire information, in which specific information for identifying a questionnaire respondent included in the questionnaire contents overlaps into one data. , the analysis step may be performed after the integration step.

The identification code may be printed on a handout distributed to the survey subjects, and the submission may be included in the handout.

One aspect of the present invention includes a communication processing unit that acquires, through communication, first questionnaire information indicating questionnaire contents input through a web page displayed on a terminal of a questionnaire subject who has read an identification code; an input processing unit that accepts input of second questionnaire information obtained by converting questionnaire contents written by hand or print into a data format into a submission; and the questionnaire contents of each of the first questionnaire information and the second questionnaire information. This is a questionnaire analysis device that includes an analysis section that executes an analysis process that analyzes the information and assigns a classification according to the content.

One aspect of the present invention provides a communication function that acquires, through communication, first questionnaire information indicating the questionnaire contents input through a web page displayed on a terminal of a questionnaire subject who has read an identification code; An input function that accepts the input of second questionnaire information obtained by converting the questionnaire contents written in handwriting or printing on the submission into a data format, and an analysis of the questionnaire contents of each of the first questionnaire information and the second questionnaire information. This is a program that causes a computer to execute an analysis function that executes an analysis process that assigns a classification according to the content.

According to the questionnaire analysis method, questionnaire analysis device, and program of the present disclosure, it is possible to realize questionnaire analysis based on responses from a wide range of questionnaire subjects, regardless of the presence or absence of a terminal.

1 is a schematic diagram of a questionnaire system to which a tabulation device according to an embodiment of the present invention is applied. FIG. 2 is a schematic diagram showing an example of a handout distributed to survey respondents. FIG. 2 is a schematic diagram showing an example of a questionnaire screen displayed on a mobile device through an identification code of a distribution item. FIG. 1 is a schematic diagram showing an example of the hardware configuration of a questionnaire analysis device. FIG. 2 is a block diagram showing an example of a functional configuration of a questionnaire analysis device. 3 is a flowchart illustrating an example of questionnaire processing by the questionnaire analysis device. It is a block diagram showing an example of the functional composition of the questionnaire analysis device in a modification.

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

<Overall configuration>
First, the overall configuration will be described with reference to FIG. FIG. 1 is a schematic diagram of a questionnaire system 1 to which a questionnaire analysis device 10 according to an embodiment of the present invention is applied. Note that in this specification, the term "system" refers to an overall device composed of a plurality of devices, a plurality of means, and the like.

The questionnaire system 1 of this embodiment distributes questionnaire handouts 100 to questionnaire subjects. In this example, the distribution material 100 is distributed to residences 2a, 2b, and 3 existing in the target area. The distribution material 100 is, for example, directly distributed by Company A, which manages the questionnaire, or indirectly distributed using a delivery company or by mail. In this way, various methods can be used for distribution, such as newspaper inserts, mail, and posting. In the figure, only three houses are shown, but the number of houses to which the distribution is made is not limited to this. Further, the distribution destination of the distribution material 100 is not limited to residences, but may be distributed directly to questionnaire subjects in the city or the like.

The distribution 100 includes a postcard 110 for returning the questionnaire and an identification code 115. FIG. 2 is a schematic diagram showing an example of a handout 100 distributed to survey respondents.

The handout 100 shown in FIG. 2 includes a client display section 101 that shows the person requesting the questionnaire, a request display section 102 that shows the request text for the questionnaire, a gift display section 103 that shows the possibility that the survey target will receive a present, and a questionnaire. It has an organizer display section 104 indicating the organizer who is hosting the survey, a deadline display section 105 indicating the deadline for the questionnaire, and a postcard 110.

The postcard 110 is a submission for the questionnaire subject to write the questionnaire by hand. The postcard 110 is, for example, a part of the distribution material 100, and can be used by cutting it out with scissors or the like. In this example, the delivery destination of the postcard 110 is set in advance to Company A, which is the sponsor of the questionnaire, and the delivery cost is paid in advance or after the fact. Therefore, the survey respondents can deliver the answers to the survey to Company A without paying any fees.

The postcard 110 has a questionnaire entry column 111 in which the questionnaire subject writes the contents of the questionnaire for company B, a delivery destination entry column 112 in which the recipient of the present is entered, and an identification code 115. In this example, the identification code 115 is displayed inside the questionnaire entry column 111 of the postcard 110.

The identification code 115 is, for example, a code such as a QR code (registered trademark) that can be read with a camera. When the identification code 115 is read by the terminal 5 having a camera function, it presents the terminal 5 with information for transitioning to a web page for inputting the questionnaire. The identification code 115 is not limited to a two-dimensional code such as a QR code (registered trademark), but may also use a one-dimensional barcode.

When the questionnaire subject reads the identification code 115 using the camera function of the terminal 5 such as a smartphone, the screen of the terminal 5 transitions to a web page for inputting the questionnaire. FIG. 3 is a schematic diagram showing an example of a questionnaire screen displayed on the terminal 5 through the identification code 115 of the distribution material 100.

The web page shown in FIG. 3 includes a request display section 121 that displays text requesting the questionnaire, an application period display section 122 that indicates the application period, a present display section 123 that explains the present for the survey sender, and a survey target person. It has a questionnaire input section 131 for entering the contents of the questionnaire, a name input section 132 for entering the name, and an address input section 133 for entering the destination of the present.

In this embodiment, the questionnaire input section 131 is in a free entry format. Information input into each of the questionnaire input section 131, name input section 132, and address input section 133 is acquired by the questionnaire analysis device 10 as questionnaire information. In addition, the questionnaire information may be in a format in which input through the terminal 5 is saved in editable data stored on the cloud, or the questionnaire information can be input to the questionnaire subjects according to the form for inputting the questionnaire provided by the web page. It may also be a format in which input is performed by the user.

Next, the questionnaire analysis device 10 will be explained. The questionnaire analysis device 10 of this embodiment analyzes and manages data collected by two types of methods: a questionnaire physically sent by mail, etc., and a questionnaire converted into data through a terminal 5 such as a smartphone. It's a computer. In the example of FIG. 1, the questionnaire subjects at residence 2a respond to the questionnaire through the terminal 5a, and the questionnaire subjects at residence 2b respond to the questionnaire through the terminal 5b. Furthermore, the questionnaire subjects in residence 3 do not use the terminal 5, but respond to the questionnaire by mailing postcards 110.

<Hardware configuration>
Referring to FIG. 4, the hardware configuration of the questionnaire analysis device 10 will be described. FIG. 4 is a block diagram showing an example of the hardware configuration of the questionnaire analysis device 10 of this embodiment. As shown in FIG. 4, the questionnaire analysis device 10 includes a processor 11, a ROM (read-only memory) 12, a RAM (random-access memory) 13, an auxiliary storage device 14, a communication I/F (interface) 15, an input device 16 and a display device 17. Each part of the hardware constituting the questionnaire analysis device 10 is connected by a bus or the like.

The processor 11 is a central part of a computer that performs calculations and control processes necessary for the operation of the questionnaire analysis device 10, and performs various calculations and processes. The processor 11 is, for example, a CPU (central processing unit), an MPU (micro processing unit), an SoC (system on a chip), a DSP (digital signal processor), a GPU (graphics processing unit), an ASIC (application specific integrated circuit), This may be a PLD (programmable logic device) or an FPGA (field-programmable gate array). Alternatively, processor 11 is a combination of more than one of these. Further, the processor 11 may be a combination of these and a hardware accelerator or the like.

The processor 11 controls each part to realize various functions based on programs such as firmware, system software, and application software stored in the ROM 12 or the auxiliary storage device 14 or the like. Furthermore, the processor 11 executes processing to be described later based on the program. Note that part or all of the program may be incorporated into the circuit of the processor 11.

The ROM 12 and the RAM 13 are main storage devices of a computer with the processor 11 at its core. The ROM 12 is a nonvolatile memory used exclusively for reading data. The ROM 12 stores, for example, firmware among the above programs. The ROM 12 also stores data used by the processor 11 to perform various processes. The RAM 13 is a memory used for reading and writing data. The RAM 13 is used as a work area for storing data temporarily used by the processor 11 to perform various processes. RAM 13 is typically volatile memory.

The auxiliary storage device 14 is, for example, an EEPROM (electric erasable programmable read-only memory), an HDD (hard disk drive), or a flash memory. The auxiliary storage device 14 stores, for example, system software and application software among the above programs. Further, the auxiliary storage device 14 stores data used by the processor 11 to perform various processes, data generated by the processes in the processor 11, various setting values, and the like.

The communication I/F 15 is an interface for communicating with an external device such as the terminal 5. The input device 16 is a means for accepting user operations, and is composed of a keyboard, a touch panel, or the like. The display device 17 is a means for outputting various information to the user, and is constituted by a display. The input device 16 and the display device 17 may be configured by a touch panel display.

<Functional configuration>
The questionnaire analysis device 10 implements various functional units using the above-described hardware configuration. With reference to FIG. 5, among the functional units implemented on the questionnaire analysis device 10, the functions related to the questionnaire will be described. FIG. 5 is a block diagram showing an example of the functional configuration of the questionnaire analysis device 10. As shown in FIG.

The questionnaire analysis device 10 of this embodiment includes, as functional units implemented on the processor 11, a communication processing unit 31, an input processing unit 32, a data integration unit 33, an analysis unit 34, a journal processing unit 35, An output processing section 36 is provided.

The communication processing unit 31 executes a process of communicating with an external computer and transmitting and receiving data. In this embodiment, the communication processing unit 31 acquires questionnaire information regarding the questionnaire input through the terminal 5 through communication. Hereinafter, the questionnaire information acquired by the communication processing unit 31 through the terminal 5 will be described as first questionnaire information.

In the example of FIG. 4, the communication processing unit 31 acquires first questionnaire information including information input to each of the questionnaire input unit 131, name input unit 132, and address input unit 133. That is, the first questionnaire information in this example includes the questionnaire contents and the name and address of the questionnaire respondent who input the questionnaire contents.

The input processing unit 32 executes processing for receiving data and operations on the input device 16 by an operator of the questionnaire analysis device 10 or the like. In this embodiment, the input processing unit 32 executes a process of receiving, as questionnaire information, the contents of a questionnaire written by hand or printed by the questionnaire subject who received the handout 100. Hereinafter, the questionnaire information that the input processing unit 32 acquires based on the information written on the handout 100 will be described as second questionnaire information.

The second questionnaire information may be in a format in which an operator visually confirms the text information and the input device 16 inputs text information through another computer, or it may be included in image data scanned using a technology such as OCR (Optical Character Recognition). It may also be in a format that reads characters and automatically converts them into digital text. In this way, the format in which the input processing unit 32 receives the second questionnaire information is not particularly limited.

In the example of FIG. 3, the input processing unit 32 converts the contents written in the questionnaire entry field 111 and the delivery address entry field 112 into data and acquires the data as second questionnaire information. That is, the second questionnaire information in this example includes the questionnaire contents written in the questionnaire writing column 111 and the address and name of the questionnaire respondent written in the delivery address writing column 112.

The input processing unit 32 also performs image processing to present data that reproduces the handwriting, drawings, etc. of the questionnaire respondents as a sample of the questionnaire to the questionnaire requester (for example, Company B). In this image processing, a masking process is performed on the image data obtained by reading the postcard 110 to mask personal information such as a name and address. This allows survey respondents to more intuitively communicate their wishes to Company B through letters and pictures actually written and drawn, while protecting personal information.

The data integration unit 33 executes processing for integrating the first questionnaire information obtained through the communication processing of the communication processing unit 31 and the second questionnaire information obtained through the input processing of the input processing unit 32. In the present embodiment, the data integration unit 33 determines whether or not there is any overlap based on information for identifying a questionnaire target person associated with each of the first questionnaire information and the second questionnaire information. If there is any overlap, the data integration unit 33 performs integration processing such as deleting any information or combining questionnaire contents.

The information for identifying the person to be surveyed is, for example, an address, a name, or both. If only the address is used as information for identifying the survey target, the survey target can be set to residential units. If only the name is used as information for identifying the survey target, the survey target can be individualized regardless of address. Furthermore, when both an address and a name are used as information for identifying a person to be surveyed, it is possible to distinguish between people with the same gender and the same name compared to when only the name is used.

Note that a name matching process may be performed for at least one of the first questionnaire information and the second questionnaire information input to the data integration unit 33 to unify the address notation. For example, even if the address is the same location, the notation may vary depending on the person who entered or wrote the address, using hiragana, katakana, or kanji. By performing name matching processing, data that does not completely match as character strings is normalized.

The analysis unit 34 analyzes the questionnaire contents included in the questionnaire information and sets a classification corresponding to the analysis. The analysis unit 34 performs analysis processing on both the questionnaire information acquired through the communication processing of the communication processing unit 31 and the questionnaire information acquired through the input processing of the input processing unit 32. Note that the analysis unit 34 does not need to distinguish between the first questionnaire information and the second questionnaire information. Hereinafter, if the explanation is common to the first questionnaire information and the second questionnaire information, it may be simply explained as questionnaire information.

The content of the questionnaire is free text. Questionnaire classifications are words that concisely express the meaning of the sentences that are the contents of the questionnaire. The classification of the questionnaire is, for example, price, service, equipment, area, etc. Price is a classification that means that the content of the questionnaire includes information regarding the price of the product. Service is a classification that includes information regarding customer service by employees and staff. Facilities is a classification that means that the contents of the questionnaire include information regarding facilities such as store toilets. Area is a classification indicating that the questionnaire includes information regarding location, convenience, etc. Note that the classification shown here is just an example, and can be set as appropriate depending on the purpose and use of the questionnaire.

The analysis process by the analysis unit 34 is performed using so-called AI (Artificial Intelligence) technology. The analysis process is executed by a learning model constructed by machine learning such as supervised learning, unsupervised learning, and reinforcement learning, for example.

The case of using supervised learning will be explained. A large dataset is prepared, with the contents of the questionnaire as input information and the classifications indicated by the contents of the questionnaire as output information. The contents of the questionnaire used as the data set are also free-text sentences, and the classification is words and sentences that concisely express the meaning of the sentences that are the contents of the questionnaire.

Note that the analysis processing by the analysis unit 34 is not limited to a configuration that uses AI technology such as machine learning. The analysis process by the analysis unit 34 includes, for example, constructing an algorithm using a programming language based on the words (keywords) and combinations of sentences, etc., and using the algorithm to set classifications (tags) corresponding to the survey content. You may.

Furthermore, the analysis unit 34 can also execute a consideration process for considering whether or not the population is correct for the data group of the integrated first questionnaire information and second questionnaire information. In the consideration process, the analysis unit 34 acquires distribution information indicating the distribution destination and distribution time of the distribution material 100, and determines whether the data groups of the first questionnaire information and the second questionnaire information are valid data based on the distribution information. Determine whether or not. For example, if the distribution destination information indicates that city A has 1,000 distribution destinations and city B has 1,000 distribution destinations, the number of responses from city A is 300, but the response from city B is If the first value is 0, the analysis unit 34 determines that there is a problem with the data group, such as the need for proper distribution to City B. Alternatively, if the distribution information indicates that the distribution time is February and the questionnaire response date and time is January, the analysis unit 34 determines that a problem has occurred in the data group. The analysis unit 34 continues processing if there is no discrepancy between the distribution information and the data group in terms of distribution location or timing, and if a discrepancy occurs, outputs an alarm indicating that there is a problem with the data group. do.

The journal processing unit 35 executes a process of organizing the questionnaire information based on the classification (tag) analyzed by the analysis unit 34. A plurality of pieces of questionnaire information are grouped by classification by the journal processing unit 35.

The output processing unit 36 executes a process of outputting the questionnaire information grouped by the journal processing unit 35. The output processing unit 36 may simply generate data that summarizes the grouped questionnaire information, transmit it to an external computer, or print it on a recording medium such as paper. Further, the output processing unit 36 may output questionnaire information grouped based on a preset format or learning model in a report format.

Next, with reference to FIG. 6, a series of flowcharts of the questionnaire processing will be described. FIG. 6 is a flowchart showing an example of questionnaire processing by the questionnaire analysis device 10.

In step S101, the communication processing unit 31 executes a process of receiving first questionnaire information based on information input through the terminal 5 that read the identification code 115 of the distribution material 100. The communication processing unit 31 may acquire a plurality of pieces of first questionnaire information at the same timing after the application period has elapsed, or may acquire the pieces of first questionnaire information one after another at the timing when the first questionnaire information is input. In this way, the timing of acquiring the first questionnaire information is not particularly limited.

In step S102, the input processing unit 32 obtains second questionnaire information obtained by converting the descriptions in the questionnaire entry field 111 and the recipient address entry field 112 of the postcard 110 of the distribution material 100 into data. The input processing unit 32 may acquire a plurality of pieces of second questionnaire information at the same timing after the application period has passed, or may acquire them sequentially at the timing when the questionnaire contents of the distribution material 100 are converted into a data format. In this way, the timing of acquiring the second questionnaire information is not particularly limited.

In step S103, the data integration unit 33 aggregates the first questionnaire information obtained via the terminal 5 and the second questionnaire information obtained via the postcard 110. The data integration unit 33 executes an integration process of combining duplicate information (addresses) for identifying survey subjects out of the aggregated questionnaire information into one, or deleting one of them.

In step S104, the analysis unit 34 performs analysis processing on the aggregated questionnaire information and adds tag information to the questionnaire information.

In step S105, the journal processing unit 35 groups the aggregated questionnaire information based on the tag information.

In step S106, the output processing unit 36 outputs the grouped questionnaire information as a report or the like.

As explained above, in the questionnaire analysis method of this embodiment, the first questionnaire information indicating the questionnaire contents input through the web page displayed on the terminal 5 of the questionnaire subject who read the identification code 115 is obtained through communication. a communication step, an input step for receiving input of second questionnaire information obtained by converting the questionnaire contents written in handwriting or printing on a postcard 110 (submission) submitted by the questionnaire subject into a data format, and an input step of accepting the input of the first questionnaire information and The method includes an analysis step of analyzing the contents of each questionnaire of the second questionnaire information and performing an analysis process of assigning a classification according to the contents.

The questionnaire analysis device 10 of the present embodiment also includes a communication processing unit that acquires, through communication, first questionnaire information indicating the contents of the questionnaire input through the web page displayed on the terminal 5 of the questionnaire subject who has read the identification code 115. 31, an input processing unit 32 that accepts input of second questionnaire information obtained by converting the questionnaire contents written by hand or print on a postcard 110 (submission) submitted by the questionnaire subject into a data format, and first questionnaire information. and an analysis unit 34 that executes analysis processing for analyzing the contents of each questionnaire of the second questionnaire information and assigning a classification according to the contents.

The program of this embodiment also includes a communication function for acquiring, through communication, first questionnaire information indicating the questionnaire contents input through a web page displayed on the terminal 5 of the questionnaire subject who has read the identification code 115; an input function that accepts input of second questionnaire information obtained by converting the questionnaire contents written by hand or print on a postcard 110 (submission) submitted by a person into a data format, and each of the first questionnaire information and the second questionnaire information. The computer executes an analysis function that analyzes the contents of the questionnaire and performs an analysis process that assigns classifications according to the contents.

By using the questionnaire analysis method, questionnaire analysis device, and program configured as described above, it is possible to realize questionnaire analysis based on responses from a wide range of questionnaire subjects, regardless of the presence or absence of a terminal.

In addition, in the analysis step of this embodiment, analysis processing is performed based on a learning model that has undergone learning processing based on a dataset that uses the questionnaire content as input information and the classification corresponding to the questionnaire content as output information. . This makes it possible to accurately and quickly classify questionnaires using machine learning such as supervised learning.

Further, in this embodiment, the questionnaire contents input through the web page are in a free entry format, and the questionnaire entry column 111 in which the questionnaire contents are written or printed on the postcard 110 is in a free entry format. This allows the computer to perform the task of confirming the contents of the questionnaire, which is a free entry format, so that the analysis of the questionnaire contents can be made more efficient. By using machine learning as in this embodiment, even sentences such as natural sentences can be accurately classified using a learning model without constructing complex logic that takes into account thesaurus such as synonyms and synonyms. can be granted.

In addition, in this embodiment, integration processing is performed to integrate data in which specific information for identifying survey respondents included in the survey content overlaps into one data among the first survey information and the second survey information. The method further includes the step of analyzing, the step of analyzing being performed after the step of integrating. This makes it possible to avoid duplication of answers from the same questionnaire subject and to perform more accurate questionnaire analysis. Furthermore, even when a product or service is given away by lottery from survey respondents, it is possible to eliminate duplication and achieve a fair lottery.

Further, in the present embodiment, the identification code 115 is printed on the handout 100 distributed to the questionnaire subjects, and the postcard 110 as the submission is included in the handout 100. Thereby, by distributing the handout 100, it is possible to provide the questionnaire subjects with two options: an answer using the terminal 5 and an answer using submission of a postcard or the like.

Although one embodiment of the present invention has been described above, the present invention is not limited to the content of the above embodiment. For example, the process flow described in the flowchart of FIG. 6 is just an example. For example, the processes in step S101 and step S102 may be executed in parallel, or the order may be reversed. Furthermore, the integration process in step S103 may be performed in parallel with the processes in step S101 and step S102. In this way, the timing of processing can be changed as appropriate.

A modification of the above embodiment will be described with reference to FIG. FIG. 7 is a block diagram showing an example of the functional configuration of the questionnaire analysis device 10a in a modified example. As shown in FIG. 7, the questionnaire analysis device 10a of the modified example differs from the questionnaire analysis device 10 of the above embodiment in that it does not include the data integration section 33. Therefore, in the modified example, the integration process by the data integration unit 33 as described in the process of step S103 in FIG. 6 is not performed. It is assumed that the configuration of the questionnaire analysis device 10a other than the data integration unit 33 is the same as the configuration of the questionnaire analysis device 10 of the above embodiment. In the modified questionnaire analysis device 10a, duplicate questionnaire subjects are excluded based on specific information (for example, address) for specifying the questionnaire subjects at a stage prior to input processing. In this way, part of the configuration of the questionnaire analysis device 10a of the above embodiment can be omitted.

Although one embodiment and a modified example of the present invention have been described above, the present invention is not limited to the above-described embodiment, and further modifications, improvements, etc. can be made within the scope of achieving the purpose of the present invention. It is included in the invention. For example, in the above embodiment, the questionnaire is a free entry method, but the method of the questionnaire is not limited to this. It may also be an item-selection type questionnaire in which items such as age, number of people in the household, and frequency of store usage are selected. The item selection questionnaire can be applied to both web pages and distributed materials (submitted materials).

The series of processes described above can be executed by hardware or software. In other words, the above-described functional blocks are merely examples and are not particularly limited. That is, it is sufficient that the computer or system has a function that can execute the series of processes described above as a whole, and the type of functional block used to realize this function is not particularly limited to the above-mentioned example. Furthermore, the location of the functional blocks is not particularly limited, and may be arbitrary. For example, the functional blocks of the questionnaire analysis device 10 may be transferred to another device. Conversely, functional blocks of other devices may be transferred to the questionnaire analysis device 10. Further, one functional block may be configured by a single piece of hardware, a single piece of software, or a combination thereof.

When a series of processes is executed by software, a program constituting the software is installed on a computer or the like from a network or a recording medium. The computer may be a computer built into dedicated hardware. Further, the computer may be a computer that can execute various functions by installing various programs, such as a server, a general-purpose smartphone, or a personal computer. Furthermore, when handling large amounts of data, techniques such as quantum computers may be used. Furthermore, the recording medium containing the program may be configured as a medium distributed separately from the device main body in order to provide the program to the user etc., or may be provided to the user etc. in a state that is pre-installed in the device main body. It may be a recording medium. Since the program can be distributed via a network, the recording medium may be mounted on or accessible from a computer connected or connectable to the network.

Note that in this specification, descriptions regarding programs include not only processes that are performed in chronological order, but also processes that are not necessarily processed in chronological order but are executed in parallel or individually.

1 Questionnaire system 10, 10a Questionnaire analysis device 31 Communication processing section 32 Input processing section 33 Data integration section 34 Analysis section 35 Journal processing section 36 Output processing section 100 Distribution material 115 Identification code

Claims (7)

a communication step of acquiring, through communication, first questionnaire information indicating the contents of the questionnaire input through a web page displayed on the terminal of the questionnaire subject who read the identification code;
an input step of accepting input of second questionnaire information obtained by converting the questionnaire contents written in handwriting or printing on the submission submitted by the questionnaire subject into a data format;
In order to integrate the first questionnaire information obtained through communication processing and the second questionnaire information obtained through input processing, among the first questionnaire information and the second questionnaire information, a questionnaire included in the questionnaire content is selected. an integration step of performing an integration process to integrate data with duplicate addresses as specific information for identifying a respondent into one;
After the integration process, an analysis step of analyzing the questionnaire content of each of the first questionnaire information and the second questionnaire information and performing an analysis process of assigning a classification according to the content;
Survey analysis methods including.
In the analysis step,
The analysis process is performed based on a learning model that has undergone a learning process based on a dataset that uses the questionnaire content as input information and the classification corresponding to the questionnaire content as output information,
The questionnaire analysis method according to claim 1.
The questionnaire content entered through the web page is in a free entry format,
The column for writing or printing the questionnaire contents in the submission is a free entry format;
The questionnaire analysis method according to claim 1 or 2.
The identification code is printed on handouts distributed to the survey respondents,
said submission is included in said distribution;
The questionnaire analysis method according to claim 1 or 2.
Obtaining distribution information indicating the distribution destination of the distribution item, and determining whether the data group of the first questionnaire information and the second questionnaire information is valid data based on the distribution information and the number of responses to the questionnaire. further comprising a consideration processing step of
The questionnaire analysis method according to claim 4 .
a communication processing unit that acquires, through communication, first questionnaire information indicating the contents of the questionnaire input through a web page displayed on the terminal of the questionnaire subject who read the identification code;
an input processing unit that accepts input of second questionnaire information obtained by converting the questionnaire contents written in handwriting or printing on the submissions submitted by the questionnaire subjects into a data format;
In order to integrate the first questionnaire information obtained through communication processing and the second questionnaire information obtained through input processing, among the first questionnaire information and the second questionnaire information, a questionnaire included in the questionnaire content is selected. a data integration unit that executes integration processing to integrate data with duplicate addresses as specific information for identifying a respondent into one;
After the integration process, an analysis unit that executes an analysis process that analyzes the questionnaire content of each of the first questionnaire information and the second questionnaire information and assigns a classification according to the content;
A questionnaire analysis device equipped with.
a communication function that obtains, through communication, first questionnaire information indicating the questionnaire contents input through a web page displayed on the terminal of the questionnaire subject who read the identification code;
an input function that accepts the input of second questionnaire information obtained by converting the questionnaire contents written in handwriting or printing on the submissions submitted by the questionnaire subjects into data format;
In order to integrate the first questionnaire information obtained through communication processing and the second questionnaire information obtained through input processing, among the first questionnaire information and the second questionnaire information, a questionnaire included in the questionnaire content is selected. a data integration function that executes integration processing to integrate data with duplicate addresses as specific information for identifying respondents into one;
After the integration process, an analysis function that executes an analysis process that analyzes the questionnaire content of each of the first questionnaire information and the second questionnaire information and assigns a classification according to the content;
A program that causes a computer to execute.