JP2020107283A - Information processor, information processing method, program - Google Patents

Abstract

To provide a mechanism for enhancing search efficiency when searching by voice recognition.SOLUTION: The mechanism narrows down customer data to be searched for a search target group determined by a search expression part 402 corresponding to the search condition on the basis of a priority determined for an overlapped search target when searching using a character string obtained by recognizing a voice spoken to a client 101 and a search condition designated by a user, and search customer data having high similarity with the character string obtained by recognizing the voice for the narrowed down customer data.SELECTED DRAWING: Figure 4

Description

The present invention relates to a technique for performing inspection by voice recognition.

Voice input can be input faster than a keyboard or touch panel, or can be input even when the user's hands are occupied. Therefore, it is increasingly used in business operations in business organizations.

For example, in the case where the salesperson checks the route to the visited place, when the name of the customer is uttered, the uttered voice is converted into a character string, the customer matching the character string is searched, and the transaction is performed from the current location. It is possible to use it by displaying the route to the destination.

Thus, while voice input provides convenient operability to the user, its use effect depends on the recognition accuracy of whether the input voice is converted into a character string that matches the user's intention. To do.

For example, misrecognition forces the user to speak multiple times until the intended result is achieved. This loses the advantage of voice input, which is faster input.

Although the recognition accuracy of voice input is improving day by day, noise is likely to be mixed in a use environment where there is noise in the surroundings such as a place where people go out, and the possibility of erroneous recognition cannot be excluded.

Therefore, Patent Document 1 discloses a method of displaying a plurality of similar search result candidates for a character string that is erroneously recognized and selecting a search result intended by the user by clicking or tapping.

JP, 2012-22251, A

As a method of extracting search result candidates, Patent Document 1 describes a method of calculating the similarity with respect to the search target data in the database and displaying the similarity in descending order of similarity.

By using this method, even if there is an erroneous recognition, it is possible to save the trouble of uttering many times by selecting the search result intended by the user from the search result candidates by clicking or tapping.

However, when the search target data exceeds tens of thousands, displaying the search result candidates to the user becomes slow when the similarity of all of them is calculated.

In addition, there is a problem that it is inefficient to calculate the similarity for data that does not correspond to the search result.

For example, in the case where the above-mentioned salesperson checks the route to the destination, the salesperson at the Tokyo head office often looks up the business partner in the suburbs of Tokyo. In that case, the search target is the business partner in a remote place such as Osaka. Is inefficient.

Therefore, it is desirable to calculate the similarity from the data group that is highly likely to correspond to the search result intended by the user among the verification target data.

Therefore, an object of the present invention is to provide a mechanism for improving the search efficiency when performing a search by voice recognition.

The present invention for achieving the above object is an information processing device for performing a search using a character string obtained by voice recognition, wherein search target data is provided so as to correspond to each search condition among a plurality of search conditions. Storage means for classifying and storing, and search means for performing a search using the character string obtained by the voice recognition for the search target data classified by the storage means corresponding to the specified search condition, It is characterized by having.

According to the present invention, there is an effect that it is possible to enhance the search efficiency when performing a search by voice recognition.

It is a figure showing an example of a system configuration of a business partner search system. It is a block diagram showing an example of hardware constitutions of a client, a business system server, and a voice recognition server. It is a flowchart which shows the flow of an example of a search process of a supplier. It is a block diagram which shows the structure of a search setting table, and a figure for demonstrating grouping of a search object. It is a block diagram which shows an example of a structure of a supplier table and a search history table. It is a block diagram which shows the structure of an example of a search screen. It is a block diagram which shows the structure of an example of a search result screen.

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

FIG. 1 is a diagram showing an example of a system configuration of a supplier search system 100 according to the embodiment of the present invention.

A supplier search system 100 of the present invention is configured by connecting a client 101, a business system server 102, and a voice recognition server 103 on a network.

The client 101 is assumed to be a personal computer such as a smart device or a notebook PC, and receives an utterance from the user and displays a screen to the user.

The business system server 102 has a database for storing business partner data, and when a search request by a business partner name is received from a user, the business system server 102 returns business partner data matching the request.

The voice recognition server 103 receives voice data uttered by the user to the client 101, recognizes the voice data, converts the voice data into a character string, and returns the character string.

In the embodiment of the present invention, the voice recognition server 103 is assumed to use a voice recognition API of a cloud service or a voice recognition product.

Since noise is mixed in the voice data spoken in a noisy environment such as a place where the user is outside, the character string intended by the user cannot always be returned as a recognized character string.

The network 104 connects each server and the information processing device so that they can communicate with each other. It is realized by LAN (Local Area Network) for the same company, and by the Internet when connecting to a server between company organizations.

FIG. 2 is a block diagram showing an example of the hardware configuration of the client 101 and the business system server 102 according to the embodiment of the present invention.

As illustrated in FIG. 2, the information processing apparatus includes a CPU (Central Processing Unit) 201, a ROM (Read Only Memory) 202, a RAM (Random Access Memory) 203, an input controller 205, a video controller 206, via a system bus 204. A memory controller 207 and a communication I/F controller 208 are connected.

The CPU 201 centrally controls each device and controller connected to the system bus 204.

The ROM 202 or the external memory 211 is a control program executed by the CPU 201, such as a BIOS (Basic Input/Output System), an OS (Operating System), a computer-readable executable program for implementing this information processing method, and various necessary programs. Holds data (including data table).

The RAM 203 functions as a main memory, a work area, etc. of the CPU 201. The CPU 201 loads various programs necessary for executing the processing from the ROM 202 or the external memory 211 into the RAM 203, and executes the loaded programs to realize various operations.

The input controller 205 controls input from an input device 209 such as a keyboard or a pointing device such as a mouse (not shown).

When the input device is a touch panel, the user can give various instructions by pressing (touching with a finger or the like) in accordance with an icon, a cursor, or a button displayed on the touch panel.

Further, the touch panel may be a touch panel such as a multi-touch screen capable of detecting a position touched by a plurality of fingers.

The video controller 206 controls display on an external output device such as the display 210.

The display shall include the display of a laptop computer integrated with the main body.

The external output device is not limited to the display, and may be a projector, for example. An input device is also provided for the device that can accept the touch operation described above.

Note that the video controller 206 can control a video memory (VRAM) for performing display control, can use part of the RAM 203 as a video memory area, or can be provided with a dedicated video memory separately. It is possible.

The memory controller 207 controls access to the external memory 211. The external memory is connected to an external storage device (hard disk), a flexible disk (FD), or a PCMCIA card slot that stores a boot program, various applications, font data, user files, edit files, and various data via an adapter. A compact flash (registered trademark) memory or the like can be used.

The communication I/F controller 208 connects and communicates with an external device via a network, and executes communication control processing on the network.

For example, communication using TCP/IP, communication using a telephone line such as ISDN, and communication using a 3G line of a mobile phone are possible.

Note that the CPU 201 enables display on the display 210, for example, by executing outline font rasterization processing in the display information area in the RAM 203. Further, the CPU 201 enables a user instruction using a mouse cursor or the like (not shown) on the display 210.

Next, with reference to the flowchart shown in FIG. 3, a supplier search process executed by the supplier search system according to the embodiment of the present invention will be described.

The flowchart shown in FIG. 3 is a process in which the CPU 201 of the client 101 and the business system server 102 reads and executes a predetermined control program, and is a flowchart showing a process of displaying a route from the voice input reception to the customer.

In step S301, the CPU 201 of the client 101 receives the voice of the customer name uttered by the user.

FIG. 6 shows an example of the configuration of the search screen 601 displayed when the user speaks. The search screen 601 is configured to include a message to speak and a search condition 602.

The search condition 602 sets the search condition desired by the user, and the search condition displays the character string of the search expression part description (for user display) 403. The search condition selected by the user is used when creating the search expression in step S304.

As shown in FIG. 6, as a search condition, for example, a customer searched in the past, a customer who is 10 km or more away from the sales office, or a new customer who can be enjoyed by the system. A user who is within 6 months after registration, or a user who uses it can select at least one or more conditions for narrowing down the search target, but it is also possible to search without selecting.

In step S302, the CPU 201 of the client 101 transmits the voice accepted in step S301 to the voice recognition server 103 to request the voice recognition result. Then, the recognition character string is received from the voice recognition server 103 as a result of the voice recognition.

In step S303, the CPU 201 of the client 101 transmits the search condition specified by the user in step S301 and the recognition character string received in step S302 to the business system server 102, and the customer data matching the recognition character string is displayed. Request search results.

In step S304, the CPU 201 of the business system server 102 receives the search condition and the recognition character string designated by the client 101 or the user, and creates a search formula for searching the customer data that matches the recognition character string.

The search expression is created by combining the SQL (Structured Query Language) of the search expression part 402 of the search setting table 400 shown in FIG.

When the search expression parts 402 are combined, a search expression can be created by combining only the search expression parts corresponding to the search condition specified by the user in step S301.

FIG. 4 shows a search setting table 400 and a search target grouping method 404 for creating a search expression for searching for supplier data.

The search setting table 400 includes a priority order 401, a search expression part 402, and a search expression part explanation (for user display) 403, which can be set in advance by a user, an administrator, or the like.

Ascending order values are set in the priority order 401 from the record with the highest priority order, and the search expression parts 402 store search expression parts (SQL) for searching the supplier table 500.

The search expression part description (for user display) 403 stores a character string displayed when the user specifies the search condition in step S301.

An example of a method of grouping the customer data to be searched is shown at 404. In 404, it is classified into eight groups to which a priority order for calculating the similarity is assigned, and eight search expressions for extracting the search results corresponding to each group are created.

The search target grouping method 404 indicates a search target group combined with the search expression parts 402 and its priority.

In the present embodiment, assuming that all the search conditions on the search screen 601 are specified by the user in step S301, a method of creating a search expression will be described with reference to FIG.

In the circle of A, the search result of the search expression part (SQL) with the highest priority of 1 is entered.

In the circle of B, the search result of the search expression part (SQL) having the second highest priority and the priority of 2 is entered.

In the circle of C, the search result of the search expression part (SQL) of the third highest priority is entered.

Next, a method of creating a search expression (SQL) for extracting the search result of each group will be described.

The group of 1, which is the common part of A, B and C, has the highest priority.

The actual search expression (SQL) is "(search expression part of A) INTERSECT (search expression part of B) INTERSECT (search expression part of C)".

Among the common parts of A and B, the second group to which C does not belong becomes the second priority search formula.

The actual search expression (SQL) is "(A search expression part) INTERSECT (B search expression part) EXCEPT (C search expression part)".

Of the common parts of A and C, the group of 3 to which B does not belong becomes the search expression of the third priority.

The actual search expression (SQL) is "(A search expression part) INTERSECT (C search expression part) EXCEPT (B search expression part)".

Among the common parts of B and C, the group of 4 to which A does not belong becomes the search expression of the fourth priority.

The actual search formula (SQL) is "(B search formula parts) INTERSECT (C search formula parts) EXCEPT (A search formula parts)".

A group of 5 belonging to A but not to B or C becomes a search expression of fifth priority.

The actual search expression (SQL) is "(A search expression part) EXCEPT (B search expression part) EXCEPT (C search expression part)".

A group of 6 belonging to B but not A or C becomes a search expression having the sixth priority.

The actual search expression (SQL) is "(B search expression parts) EXCEPT (A search expression parts) EXCEPT (C search expression parts)".

A group of 7 belonging to C but not A or B becomes a search expression of the 7th priority.

The actual search expression (SQL) is “(C search expression parts) EXCEPT (A search expression parts) EXCEPT (B search expression parts)”.

The group of 8 that does not belong to any of A, B, and C becomes the search expression having the lowest priority.

The actual search expression (SQL) is "SELECT COMPANY_NAME FROM COMPANY EXCEPT (A search expression part) EXCEPT (B search expression part) EXCEPT (C search expression part)".

In step S305, the CPU 201 of the business system server 102 executes the search expressions created in step S304 in descending order of priority.

In step S306, the CPU 201 of the business system server 102 acquires the search result list (array of customer data) executed in step 305 from the customer table 500 (see FIG. 5).

FIG. 5 shows the configuration of the supplier table 500 and the search history table 510. The supplier table 500 stores supplier data, and has an ID 501, a supplier name 502, a supplier address 503, and sales. It consists of a distance 504 from the place and a registration date 505.

The ID 501 stores an ID for uniquely identifying the supplier, and the supplier name 502 stores the supplier name. The supplier name is used to calculate the degree of similarity with the recognized character string.

The customer address 503 stores the address of the customer. The supplier address is used as an argument for map display when displaying the route to the supplier.

The distance 504 from the sales office stores the distance (km) from the sales office. It is used as a condition when searching for a supplier who is 10 km or more away from the sales office registered as priority 2 in the search setting table 400.

As the registration date 505, the date when the customer data is registered is stored. It is used as a condition when searching for a customer who is newly registered within 6 months and is registered as priority 3 in the search setting table 400.

The search history table 510 stores the search history of the user, and includes the user ID 511 and the business partner 512 who has searched.

The user ID 511 stores the ID of the searched user, and the searched supplier 512 has the supplier name searched by the user corresponding to the user ID 511.

It is used as a condition when searching for a previously searched customer registered as priority 1 in the search setting table 400.

In step S307, the CPU 201 of the business system server 102 calculates the degree of similarity between the customer name and the recognized character string in the search result list acquired in step 306.

As an example of a method of calculating the degree of similarity, a known technique such as Levenshtein distance, which indicates how different two character strings to be compared are, is used. In the case of the Levenshtein distance, the smaller the distance, the higher the similarity.

In step S 308, the CPU 201 of the business system server 102 extracts an array of supplier data corresponding to the supplier name calculated in step S 307 with a high degree of similarity (small Levenshtein distance), and sends it to the client 101.

In step S309, the CPU 201 of the client 101 receives the array of customer data transmitted in step S308.

In step S310, the CPU 201 of the client 101 displays, on the search result screen 701, the route from the current location to the business partner address for the business partner having the highest degree of similarity in the business partner data array transmitted in step S309. To do.

The route may be displayed by using a map service such as Google Maps.

The second and subsequent customer data arrays are displayed on the search result screen 701 (see FIG. 7) as search result candidates.

FIG. 7 shows an example of the configuration of a search result screen 701 that displays the route to the customer and the search result candidates. The route display 702 and the search of the map service for showing the user the route to the customer. The result candidate 703 and the re-search area 704 for re-searching under different search conditions are included.

The route display 702 of the map service displays the route from the current position to the customer who has the highest degree of similarity on the map.

The search result candidate 703 displays, as a search result candidate, the name of the customer having the second or higher similarity degree in the customer array received by the client 101. By selecting the name of the customer, the user displays the route to the customer without speaking again.

The re-search area 704 with another search condition is used when the user wants to change the search condition and search again when the user's intended supplier does not exist in the search result screen 701 or the search result candidates 703. It has a search condition to set and a button to execute a re-search.

The user can also execute the processing from step 301 by designating another search condition on the search result screen 701 and performing a search again.

As described above, according to the embodiments of the present invention, it is possible to improve the search efficiency by voice recognition.

Although the embodiments have been described above, the present invention can be implemented as, for example, an apparatus, a method, a program, a recording medium, or the like.

Specifically, it may be applied to a system composed of a plurality of devices, or may be applied to an apparatus composed of one device.

Further, the program in the present invention is a program that allows a computer to execute the processing method of the flowchart shown in FIG. 3, and the storage medium of the present invention stores a program that allows the computer to execute the processing method in FIG. The program in the present invention may be a program for each processing method of each device in FIG.

As described above, the recording medium recording the program that realizes the functions of the above-described embodiments is supplied to the system or apparatus, and the computer (or CPU or MPU) of the system or apparatus executes the program stored in the recording medium. It goes without saying that the object of the present invention can also be achieved by reading and executing.

In this case, the program itself read from the recording medium realizes the novel function of the present invention, and the recording medium recording the program constitutes the present invention.

As a recording medium for supplying the program, for example, a flexible disk, hard disk, optical disk, magneto-optical disk, CD-ROM, CD-R, DVD-ROM, magnetic tape, non-volatile memory card, ROM, EEPROM, silicon. A disk or the like can be used.

Further, not only the functions of the above-described embodiments are realized by executing the program read by the computer, but also the OS (operating system) running on the computer is actually executed based on the instructions of the program. It goes without saying that a case where a part or all of the processing is performed and the functions of the above-described embodiments are realized by the processing is also included.

Furthermore, after the program read from the recording medium is written in the memory provided in the function expansion board inserted in the computer or the function expansion unit connected to the computer, the function expansion board is instructed based on the instruction of the program code. Needless to say, this also includes the case where the CPU or the like included in the function expansion unit performs some or all of the actual processing and the functions of the above-described embodiments are realized by the processing.

Further, the present invention may be applied to a system including a plurality of devices or an apparatus including a single device.

Further, it goes without saying that the present invention can be applied to the case where it is achieved by supplying a program to a system or an apparatus.

In this case, by reading the recording medium storing the program for achieving the present invention into the system or device, the system or device can enjoy the effects of the present invention.

Furthermore, by downloading and reading a program for achieving the present invention from a server, a database or the like on a network using a communication program, the system or apparatus can enjoy the effects of the present invention. It should be noted that the present invention also includes all configurations that combine the above-described embodiments and modifications thereof.

100 Business Partner Search System 101 Client 102 Business System Server 103 Voice Recognition Server

Claims (4)

An information processing device for performing a search using a character string obtained by voice recognition,
A storage unit that classifies and stores the search target data so as to correspond to each of the plurality of search conditions;
Search means for performing a search using the character string obtained by the voice recognition on the classified search target data of the storage means corresponding to the specified search condition;
An information processing apparatus comprising: The storage means stores information related to prioritizing a search for the search range based on search ranges overlapping with each other according to the search condition,
The search unit searches the search target data in the search range in the order of priority using the character string obtained by the voice recognition based on the information related to prioritizing the search range stored in the storage unit. The information processing apparatus according to claim 1, which is performed. A method for controlling an information processing device that performs a search using a character string obtained by voice recognition,
The information processing device is
Obtained by the voice recognition with respect to the classified search target data of the storage unit that classifies and stores the search target data so as to correspond to each search condition among the plurality of search conditions corresponding to the specified search condition. A search step for performing a search using the obtained character string,
A method for controlling an information processing device, comprising: Computer,
It is obtained by voice recognition with respect to the classified search target data of the storage unit that classifies and stores the search target data so as to correspond to each search condition among the plurality of search conditions corresponding to the specified search condition. A search means for searching using the character string
A computer program to do so.

Images