JP6867661B1 - Information processing methods, computer programs and information processing equipment - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information processing method, a computer program and an information processing device which can be expected to improve the accuracy of a search service. An information processing method is such that an information processing device that provides a search service that accepts input of a keyword for a search from a user and outputs information about one or a plurality of search targets corresponding to the keyword performs the keyword and search. The user is requested to perform the work of associating the target, and as a result of the work, the information associated with the keyword and the search target is acquired from the user, and the user who has performed the work is given a privilege. The privilege may be the right to use the search service for a predetermined period of time. The information processing device may request the user to perform the work before the predetermined period elapses. [Selection diagram] FIG. 10

Description

The present invention relates to an information processing method, a computer program, and an information processing device for providing a search service.

Conventionally, a search service that searches for information related to a keyword entered by a user and provides the search result to the user has become widespread. For example, in Patent Document 1, a search system in which a search system searches a database for a group keyword corresponding to a keyword provided by a client to a server, and the server provides the client with a search result page containing the group keyword and the keyword together with the search information corresponding to the keyword. Proposed. In this search system, when the client selects a keyword or group keyword on the search result page, the server connects the client to the web page corresponding to the network address corresponding to the selected keyword or group keyword.

Japanese Unexamined Patent Publication No. 2005-503614

In recent years, AI (Artificial Intelligence) has begun to be used for the purpose of improving the accuracy of search services. In a search service using AI, for example, it is necessary to use a learning model of a neural network and to train this learning model in advance for keywords and the like that can be used for the search. By repeating the learning of the learning model, the accuracy of the search can be expected to improve. However, in the learning process of the learning model, for example, it is necessary to create learning data in which keywords and search targets are associated with each other, which requires a great deal of labor.

The present invention has been made in view of such circumstances, and an object of the present invention is to provide an information processing method, a computer program, and an information processing device which can be expected to improve the accuracy of a search service. is there.

In the information processing method according to one embodiment, the information processing apparatus sends an execution request for a work of associating a search keyword and a search target related to the search service to a user of the search service, and the user sends the result of the work. As a result, the information associated with the keyword and the search target is acquired, and the user who has performed the work is given the right to use the search service for a predetermined period of time.

In the case of one embodiment, it can be expected that the accuracy of the search service will be improved.

It is a schematic diagram for demonstrating the outline of the information processing system which concerns on this Embodiment. It is a block diagram which shows the structure of the server apparatus which concerns on this embodiment. It is a schematic diagram which shows one configuration example of a learning model. It is a schematic diagram which shows one configuration example of a company DB. It is a schematic diagram which shows one configuration example of a user DB. It is a schematic diagram which shows one configuration example of the annotation information DB. It is a block diagram which shows the structure of the terminal apparatus which concerns on this embodiment. It is a flowchart which shows the procedure of the search process performed by the terminal apparatus which concerns on this Embodiment. It is a flowchart which shows the procedure of the search process performed by the server apparatus which concerns on this Embodiment. It is a schematic diagram which shows an example of the annotation screen. It is a flowchart which shows the procedure of annotation processing performed by the server apparatus which concerns on this Embodiment. It is a flowchart which shows the procedure of annotation processing performed by the terminal apparatus which concerns on this Embodiment.

A specific example of the information processing system according to the embodiment of the present invention will be described below with reference to the drawings. It should be noted that the present invention is not limited to these examples, and is indicated by the scope of claims, and is intended to include all modifications within the meaning and scope equivalent to the scope of claims.

<System overview>
FIG. 1 is a schematic diagram for explaining an outline of an information processing system according to the present embodiment. The information processing system according to the present embodiment is a system that provides a search service for corporate information. The user inputs a keyword related to the company on the search screen or the like displayed on the terminal device 3. The terminal device 3 transmits the keyword input by the user to the server device (information processing device) 1 that provides the search service (see arrow 101). The server device 1 includes a database that stores company information, acquires keywords entered by the user from the terminal device 3, searches the database for companies corresponding to the acquired keywords, and obtains company information by the search. Is transmitted to the terminal device 3 (see arrow 102). The terminal device 3 receives and displays the company information from the server device 1, and presents the company information corresponding to the user who has input the keyword.

The server device 1 according to the present embodiment uses so-called AI to perform a company search process according to a keyword input by the user. Although details will be described later, the AI included in the server device 1 according to the present embodiment is, for example, a learning model in which a neural network configuration is adopted, and is used in a process of determining an appropriate company for a keyword. The learning model is previously trained in the server device 1 or another device, and the learned learning model is stored in the server device 1. Since the learning model can be expected to improve accuracy (that is, output more appropriate company information in response to keyword input) by repeating the learning process (re-learning), the server according to the present embodiment. The device 1 performs a process of collecting data used for re-learning the learning model.

The process of creating data used for the learning process of the learning model, so-called teacher data, is called "annotation". In the information processing system according to the present embodiment, a request for executing the work of this annotation is transmitted to the terminal device 3 of the user (user of the search service) who uses the search service (see arrow 103). In response to this request, the terminal device 3 performs the annotation work by the user, acquires the result, and transmits the acquired annotation result to the server device 1 (see arrow 104). The server device 1 acquires and stores the result of the annotation work performed by the user from the terminal device 3. Using the annotation result stored in the server device 1, the server device 1 or another device can perform the re-learning process of the learning model. In the present embodiment, the annotation work requested to the user is the work of associating one or more keywords (search keywords) with one company (search target), but this is an example. This annotation work is also simply called work, and the result of the annotation work performed by the user corresponds to the result of the annotation work.

Further, the search service provided to the user by the information processing system according to the present embodiment is a paid service that requires a predetermined amount of usage fee to be paid for each predetermined period such as one month or one year. However, the server device 1 exempts the user who has performed the above annotation work from paying the usage fee, and grants the right to use the search service for a predetermined period as a privilege (see arrow 105). As a result, the information processing system according to the present embodiment is a search service by encouraging the user to perform annotation work, accumulating data necessary for the learning process of the learning model, and repeatedly performing the re-learning process of the learning model. It can be expected to improve the accuracy of.

In the present embodiment, the user is a user who has registered the use of the search service in advance, and is not necessarily a person (natural person), and may be a corporation such as a company or an organization. Further, the search service provided by the information processing system according to the present embodiment handles company information as a search target, but the search target is not limited to this, and the search target may be various information other than the company information. .. Further, in the present embodiment, the enterprise may include, for example, a company, an organization, a partnership, an entity, an organization, a corporation, or the like. Further, in the present embodiment, the right to use the search service is given to the privilege given to the user for the execution of the annotation work, but the present invention is not limited to this, and various benefits are given to the user. You can do it.

<Device configuration>
FIG. 2 is a block diagram showing a configuration of the server device 1 according to the present embodiment. The server device 1 according to the present embodiment includes a processing unit 11, a storage unit (storage) 12, a communication unit (transceiver) 13, and the like. In the present embodiment, it is assumed that the processing is performed by one server device 1, but a plurality of server devices 1 may be distributed to perform the processing.

The processing unit 11 is configured by using an arithmetic processing unit such as a CPU (Central Processing Unit) or an MPU (Micro-Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and the like. The processing unit 11 reads and executes the server program 12a stored in the storage unit 12 to provide the company information searched for the keyword input by the user, and requests the user to perform annotation work. Perform various processes such as processing.

The storage unit 12 is configured by using a large-capacity storage device such as a hard disk. The storage unit 12 stores various programs executed by the processing unit 11 and various data required for processing by the processing unit 11. In the present embodiment, the storage unit 12 stores the server program 12a executed by the processing unit 11 and the learning model 12b to which machine learning has been performed in advance. Further, the storage unit 12 stores a company information DB (database) 12c that stores information about the company to be searched, a user DB 12d that stores information about the user who uses the search service, and information about the result of the annotation by the user. Annotation information DB 12e is provided.

In the present embodiment, the server program 12a is provided in a mode of being recorded on a recording medium 99 such as a memory card or an optical disk, and the server device 1 reads the server program 12a from the recording medium 99 and stores it in the storage unit 12. However, the server program 12a may be written to the storage unit 12 at the manufacturing stage of the server device 1, for example. Further, for example, in the server program 12a, the server device 1 may acquire what is distributed by another remote server device or the like by communication. For example, in the server program 12a, the writing device may read what has been recorded on the recording medium 99 and write it in the storage unit 12 of the server device 1. The server program 12a may be provided in the form of distribution via the network, or may be provided in the form of being recorded on the recording medium 99.

FIG. 3 is a schematic diagram showing a configuration example of the learning model 12b. The illustrated learning model 12b has the structure of a neural network in which a plurality of neurons are interconnected. Since it is an existing technique, detailed description thereof will be omitted, but a neuron is an element that performs an operation on a plurality of inputs and outputs one value as an operation result. Neurons have information such as weighting coefficients and thresholds used in calculations. The neural network learning model 12b aggregates the input layer that accepts the input of one or more data, the intermediate layer that performs arithmetic processing on the data received by the input layer, and the arithmetic results of the intermediate layer. Alternatively, it is provided with an output layer that outputs a plurality of values.

The learning model 12b according to the present embodiment accepts one or more words or sentences as keywords as input. Further, the learning model 12b outputs the company label of the company related to the input keyword and the vector information corresponding to the input keyword in response to the input of the keyword. The company label is uniquely attached to the company, and in the present embodiment, it is, for example, an integer value from 1 to 9999. The vector information is, for example, a vector having 256 dimensions or more, which is determined according to the keyword. The learning model 12b may have a configuration in which the company label is output and the vector information is not output. Further, although the learning model 12b outputs one company label in this figure, the learning model 12b may be configured to output a plurality of company labels.

In the present embodiment, as the learning model 12b, for example, a model such as Universal Sentence Encoder or BERT (Bidirectional Encoder Representations from Transformers) can be adopted. The Universal Sentence Encoder is an encoder obtained by training models such as Attention and Transformer with learning data of multiple languages, and even if they are in different languages such as English and Japanese, even if they are input sentences with the same content. Outputs a vector with close values. Since the learning model 12b such as Universal Sentence Encoder and BERT is an existing technique, detailed description thereof will be omitted. Further, the learning model 12b is not limited to the Universal Sentence Encoder or BERT, and for example, an encoder based on an RNN (Recurrent Neural Network) and an LSTM (Long Short-Term Memory) may be adopted.

The learning model 12b stored in the storage unit 12 of the server device 1 is a trained model that has been previously trained. The learning process is a process of setting appropriate values for the coefficients, thresholds, and the like of each neuron constituting the neural network by using a large number of learning data given in advance. The learning model 12b according to the present embodiment is subjected to learning processing using learning data created based on keywords (words or sentences, etc.) extracted from, for example, a company's homepage or publication, at least at the first stage. Will be done. The learning process at this time may be so-called supervised learning that uses teacher data associated with a company label for keywords, and so-called unsupervised learning that uses keywords that are not associated with a company label as learning data. May be. The data used for the learning process may be created by the designer of this system or the like, or may be created by a device such as the server device 1. In the present embodiment, the second and subsequent learning processes (re-learning processes) of the learning model 12b are performed using the annotation information collected by the server device 1, that is, the annotation information created by the user who uses the search service.

FIG. 4 is a schematic diagram showing a configuration example of the corporate DB 12c. The company DB 12c according to the present embodiment stores information such as "company label", "company name", "company attribute information", and "detailed information" in association with each other. The "company label" is identification information uniquely attached to the company, and corresponds to the company label output by the learning model 12b. In the present embodiment, the "company label" is an integer value from 1 to 9999. In the illustrated example, the "company label" is shown as the four digits "0001" and "0002", which correspond to the integer values "1" and "2". The "company name" is a company name or the like, and is character string information. In the illustrated example, "A Co., Ltd." and "B Shoji" are shown as "company names".

"Corporate attribute information" is one or more pieces of information representing the nature or characteristics of a company. In the present embodiment, the "corporate attribute information" includes a plurality of information such as "industry" and "location". "Industry" is a type of business run by a company. In this example, "Manufacturing industry" is indicated for "A Co., Ltd." and "Import industry" is indicated for "B Shoji". The "location" is information indicating the place where, for example, the head office of a company is located. In this example, "Tokyo" is indicated for "A Co., Ltd." and "Kanagawa" is indicated for "B Shoji". In addition to the above-mentioned "industry" and "location", various information such as the number of business years, the number of employees, the number of capitals, and sales can be stored in the "corporate attribute information". The "detailed information" is information other than the "corporate attribute information" about the company, and may include various information such as images, sounds, and links in addition to the character string information. "Detailed information" includes, for example, texts such as news about a company, URL (Uniform Resource Locator) of a company's homepage, images of products handled by the company, or moving images of company advertisements (commercial, CM (Commercial Message)), etc. Various information can be stored. "Detailed information" is information presented to the user together with the search result.

FIG. 5 is a schematic diagram showing a configuration example of the user DB 12d. The user DB 12d according to the present embodiment stores information such as "user ID", "user name", "user attribute information", and "free expiration date" in association with each other. The "user ID" is identification information uniquely attached to the user, and is information based on a combination of characters, numbers, and the like. In the illustrated example, "U001" and "U002" are shown as "user ID". The "user name" is the name of the user. In the illustrated example, "user A" and "user B" are shown as "user names", but in reality, the real name of the user and the like are stored.

"User attribute information" is one or more pieces of information representing the nature or characteristics of the user. In the present embodiment, the "user attribute information" includes a plurality of information such as "industry" and "address". The "industry" is the industry of the company in which the user works. In this example, "manufacturing industry" is indicated for "user A" and "construction industry" is indicated for "user B". The "address" is information indicating the place of residence of the user, and in this example, "Tokyo" is indicated for both "user A" and "user B". In addition to the above-mentioned "industry" and "address", the "user attribute information" may include various information such as gender, age, educational background, qualifications, hobbies, and special skills.

The "free expiration date" is information regarding the expiration date during which the user can use the search service for free. In the information processing system according to the present embodiment, the user who has performed the annotation work at the request of the server device 1 is given the right to use the search service free of charge for a predetermined period of time as a privilege. The "free period" is the last day of the predetermined period that can be used free of charge given as this benefit. In this example, "User A" is "2020/8/15" and "User B" is "2020/7". / 31 "is shown.

FIG. 6 is a schematic diagram showing a configuration example of the annotation information DB 12e. The annotation information DB 12e according to the present embodiment stores information such as "company label", "company name", "keyword", and "working user" in association with each other. The "company label" and "company name" are the same as the "company label" and "company name" stored in the above-mentioned company DB 12c. In the illustrated example, a company whose "company label" is "0001" and whose "company name" is "A Co., Ltd." and whose "company label" is "0032" and whose "company name" is "N Co., Ltd." It is shown as a company.

The "keyword" is a word or the like that the user associates with the company by the work of annotation. One or more words or the like are stored in the "keyword". In the illustrated example, "A Co., Ltd." is associated with words such as "computer, artificial intelligence, ..." and "N Co., Ltd." is associated with words such as "automobile, motorcycle". There is. The "working user" is information for identifying a user who has associated a keyword with a company, and for example, a user ID attached to the user is stored. In the illustrated example, the user IDs of "U005" and "U106" are shown as "working users".

The communication unit 13 of the server device 1 communicates with various devices via a network N including an in-house LAN (Local Area Network), a wireless LAN, the Internet, and the like. In the present embodiment, the communication unit 13 communicates with the terminal device 3 used by one or more users via the network N. The communication unit 13 transmits the data given by the processing unit 11 to another device, and gives the data received from the other device to the processing unit 11.

The storage unit 12 may be an external storage device connected to the server device 1. Further, the server device 1 may be a multi-computer including a plurality of computers, or may be a virtual machine virtually constructed by software. Further, the server device 1 is not limited to the above configuration, and may include, for example, a reading unit that reads information stored in a portable storage medium, an input unit that accepts operation input, a display unit that displays an image, and the like. ..

Further, in the processing unit 11 of the server device 1 according to the present embodiment, the processing unit 11 reads and executes the server program 12a stored in the storage unit 12, so that the search processing unit 11a, the annotation processing unit 11b, and the privilege The granting unit 11c, the learning processing unit 11d, and the like are realized as software-like functional units. It should be noted that these functional parts are functional parts related to the processing of the search service and annotations, and the illustration and description of other functional parts are omitted.

The search processing unit 11a transmits the company information as a search result to the terminal device 3 for the search keyword input by the user on the terminal device 3, and performs a process of presenting the company information corresponding to the keyword to the user. The search processing unit 11a acquires the keyword input by the user from the terminal device 3. The search processing unit 11a inputs the keyword acquired from the terminal device 3 into the learning model 12b of the storage unit 12, and acquires the company label output by the learning model 12b. The search processing unit 11a reads the information about the company corresponding to the company label output by the learning model 12b from the company information DB 12c, and transmits the read information to the terminal device 3. As a result, the terminal device 3 can display the information received from the server device 1 and present the information of the company searched by the input keyword to the user.

The annotation processing unit (work request transmission unit and work result acquisition unit) 11b performs annotation processing for associating a company with a keyword in order to create learning data used for re-learning processing of the learning model 12b. In the information processing system according to the present embodiment, the annotation work is performed by the user, and the annotation processing unit 11b performs a process of requesting the user for annotation and a process of acquiring the result of the annotation by the user. In the present embodiment, the annotation processing unit 11b executes the annotation work for the user who has reached a predetermined number of days (for example, 10 days or 2 weeks) before the end of the predetermined period in which the search service can be used free of charge. Send the request. The above-mentioned predetermined period and the predetermined number of days may be the same. That is, when the period during which the user can use the search service for free begins (at the same time or immediately after), this user may be requested to perform annotation work. Further, for example, when the period during which the search service can be used free of charge ends, or after that, the user may be requested to perform annotation work. Further, for example, the annotation work may be repeatedly requested to the user every day, every three days, every week, or the like. The timing, frequency, number of times, etc. at which the annotation processing unit 11b requests the annotation work may be any timing, frequency, number of times, or the like.

At this time, the annotation processing unit 11b selects a target company for requesting annotation from the user from a plurality of companies registered in the company DB 12c. For example, the annotation processing unit 11b can count the number of times the user has viewed the company information, and preferentially select the company with the most views to be the target of annotation. Further, for example, the annotation processing unit 11b can count the number of annotations to be performed, and preferentially select a company having a small number of annotations to be annotated. Further, for example, the annotation processing unit 11b can target companies in the same industry or companies close to each other based on the user attribute information of the user requesting annotation, and targets companies whose location is close to the user's address. Can be. The method of selecting the company to be the target of these annotations is an example and is not limited to this, and the annotation processing unit 11b may select the company by any method.

The annotation processing unit 11b sets a company to be annotated and a plurality of keywords that are candidates associated with the company, and transmits the annotation to the terminal device 3 of the user who requests the annotation. At this time, the annotation processing unit 11b can use, for example, a word extracted from the homepage of this company as a candidate keyword, and for example, a word randomly selected from a set of words prepared in advance is used as a candidate keyword. be able to. Any method may be used for selecting the candidate keyword. Further, instead of presenting a candidate keyword, an arbitrary character string input may be accepted from the user and used as a keyword associated with this company.

The annotation processing unit 11b acquires the result of the user performing the annotation work, that is, the result of associating the keyword with the company from the terminal device 3 of the user who has sent the request for executing the annotation work. The annotation processing unit 11b stores the acquired result in the annotation information DB 12e of the storage unit 12.

The privilege granting unit 11c performs a process of granting a privilege to the user who has executed the request for annotation. In the information processing system according to the present embodiment, the use of the search service is charged as described above, but the privilege giving unit 11c grants the user who has performed the annotation the right to use the search service free of charge. In the privilege granting unit 11c, for example, the number of user annotations performed during a predetermined period (which may be the same as the period during which the search service can be used free of charge or may be another period) is a predetermined number. When (10 cases, 100 cases, etc.) is reached, a privilege is given to this user. The privilege granting unit 11c can grant the privilege to the user who has decided to grant the privilege by updating the "free period" of the user DB 12d so as to extend it by a predetermined period.

The learning processing unit 11d performs a process of learning the learning model 12b. The learning processing unit 11d generates teacher data for learning the learning model 12b, that is, data in which a company (company label) and a keyword are associated with each other, based on the information accumulated in the annotation information DB 12e. The result of annotations made by the user is not always correct. Therefore, the learning processing unit 11d selects the annotation result that can be determined to be correct from the information accumulated in the annotation information DB 12e, and generates teacher data.

The correctness of the annotation result can be determined by, for example, the following method. For example, it is possible to request annotations from a plurality of users for one company, and determine that the keywords associated with this company by the number of users exceeding the threshold value are the correct keywords associated with this company. Further, for example, it is possible to manage the achievements of the annotation work so far for each user, and determine the annotation result by the user who has a high achievement of correctly associating the keywords as the correct annotation result. Further, for example, it is possible to request another user to determine the correctness of the annotation result by one user, and to give a privilege to the work of the correctness determination. The correctness determination of these annotation results is an example and is not limited to this. The learning processing unit 11d may determine the correctness of the annotation result by any method, and the annotation result is determined without performing the correctness determination. It may be used to generate teacher data.

The learning processing unit 11d may perform the learning process (re-learning process) of the learning model 12b at a cycle of, for example, one week or one month. The learning process of the learning model 12b may be performed by a device different from the server device 1. In this case, the server device 1 does not have the learning processing unit 11d, and another device is the learning processing unit 11d. May be equipped.

FIG. 7 is a block diagram showing the configuration of the terminal device 3 according to the present embodiment. The terminal device 3 according to the present embodiment includes a processing unit 31, a storage unit (storage) 32, a communication unit (transceiver) 33, a display unit (display) 34, an operation unit 35, and the like. The terminal device 3 may be configured by using an information processing device such as a general-purpose personal computer, a smartphone, or a tablet-type terminal device.

The processing unit 31 is configured by using an arithmetic processing unit such as a CPU or MPU, a ROM, a RAM, and the like. The processing unit 31 reads and executes the program 32a stored in the storage unit 32 to receive a keyword for a search by the user, a process of displaying a search result according to the keyword, and a process from the server device 1. Performs various processes such as processes related to annotation work based on requests.

The storage unit 32 is configured by using, for example, a magnetic storage device such as a hard disk or a non-volatile memory element such as a flash memory. The storage unit 32 stores various programs executed by the processing unit 31 and various data required for processing by the processing unit 31. In the present embodiment, the storage unit 32 stores the program 32a executed by the processing unit 31. In the present embodiment, the program 32a is distributed by a remote server device or the like, which is acquired by the terminal device 3 by communication and stored in the storage unit 32. However, the program 32a may be written to the storage unit 32, for example, at the manufacturing stage of the terminal device 3. For example, in the program 32a, the terminal device 3 may read the program 32a recorded on the recording medium 98 such as a memory card or an optical disk and store it in the storage unit 32. For example, in the program 32a, the writing device may read what was recorded on the recording medium 98 and write it in the storage unit 32 of the terminal device 3. The program 32a may be provided in a mode of distribution via a network, or may be provided in a mode recorded on a recording medium 98.

The communication unit 33 communicates with various devices via a network N including an in-house LAN, a wireless LAN, the Internet, and the like. In the present embodiment, the communication unit 33 communicates with the server device 1 via the network N. The communication unit 33 transmits the data given by the processing unit 31 to another device, and gives the data received from the other device to the processing unit 31.

The display unit 34 is configured by using a liquid crystal display or the like, and displays various images, characters, and the like based on the processing of the processing unit 31. In the present embodiment, the display unit 34 displays various screens such as a screen for inputting a keyword for searching a company, a screen for displaying search results, and a screen for accepting annotation work.

The operation unit 35 accepts the user's operation and notifies the processing unit 31 of the accepted operation. For example, the operation unit 35 accepts a user's operation by an input device such as a mechanical button or a touch panel provided on the surface of the display unit 34. Further, for example, the operation unit 35 may be an input device such as a mouse and a keyboard, and these input devices may be configured to be removable with respect to the terminal device 3.

Further, in the terminal device 3 according to the present embodiment, the processing unit 31 reads and executes the program 32a stored in the storage unit 32, so that the search processing unit 31a, the annotation processing unit 31b, and the like become software-like functional units. It is realized in the processing unit 31. The program 32a may be a program dedicated to the information processing system according to the present embodiment, or may be a general-purpose program such as an Internet browser or a web browser.

The search processing unit 31a performs various processes related to the use of the search service of the company provided by the information processing system according to the present embodiment. The search processing unit 31a accepts the input of the search keyword from the user, and transmits the accepted keyword to the server device 1. The server device 1 searches for a company according to the keyword transmitted from the terminal device 3, and the search processing unit 31a receives the company information transmitted from the server device 1 as a search result. The search processing unit 31a displays the received company information on the display unit 34.

The annotation processing unit 31b performs processing related to the execution of annotation in response to the request from the server device 1. The annotation processing unit 31b receives the company and candidate keyword information transmitted from the server device 1 together with the annotation execution request. The annotation processing unit 31b displays on the display unit 34 a screen for performing annotation based on the received information, for example, a screen displaying (presenting) the name of the company to be annotated and a plurality of candidate keywords. On the annotation screen, the annotation processing unit 31b accepts a candidate keyword selected by the user from a plurality of candidate keywords as a keyword associated with the company. The annotation processing unit 31b transmits information in which the company to be annotated is associated with the keyword selected by the user to the server device 1 as a result of the annotation.

<Search process>
The information processing system according to the present embodiment is a system in which the server device 1 provides the user with the company information accumulated in the company DB 12c. In the present embodiment, user registration is required in advance to use the service provided by the server device 1, and the use of the service is charged. However, it may be possible to use the service free of charge for a predetermined period (for example, one week or one month) after the user first starts using the service. The user can obtain the right to use this service by paying the usage fee, but in the present embodiment, the user performs the annotation work requested by the server device 1 for a predetermined period of time. You can get the right to use this service for free.

A user who has obtained the right to use the service can use the service by starting a predetermined application program on his / her own terminal device 3 or accessing the Web page of the system with a program such as a Web browser. It can be used. For example, the user directly inputs the company name of the company that needs the information, or selects a desired company name from the list of company names and the like, so that the information of this company is displayed on the terminal device 3. be able to. Further, in the present embodiment, the user can input a keyword on the terminal device 3 and display information on one or more companies corresponding to the keyword on the terminal device 3. The terminal device 3 displays a search screen provided with a box or the like for inputting a keyword on the display unit 34, and accepts the input of the keyword from the user. The terminal device 3 transmits one or more received keywords to the server device 1 and requests a search for company information.

The server device 1 acquires the keyword input by the user in the terminal device 3, searches the company DB 12c for the company corresponding to the acquired keyword, and transmits the company information corresponding to the keyword to the terminal device 3. At this time, the server device 1 inputs the keyword acquired from the terminal device 3 into the learning model 12b of the storage unit 12, acquires the company label output by the learning model 12b, and obtains the company information corresponding to the acquired company label. Read from the company DB 12c. The learning model 12b may output a plurality of company labels, and the server device 1 may transmit company information about the plurality of companies to the terminal device 3 in response to one keyword input by the user.

The terminal device 3 receives the company information transmitted from the server device 1 in response to the input of the keyword. The terminal device 3 displays the received one or more company information on the display unit 34.

FIG. 8 is a flowchart showing the procedure of the search process performed by the terminal device 3 according to the present embodiment. The search processing unit 31a of the processing unit 31 of the terminal device 3 according to the present embodiment displays a search screen provided with, for example, a text box for inputting a keyword on the display unit 34 (step S1). The search processing unit 31a determines whether or not a search keyword has been input on the search screen (step S2). When the keyword is not input (S2: NO), the search processing unit 31a returns to step S1, maintains the display of the search screen, and waits for the keyword input. When a keyword is input (S2: YES), the search processing unit 31a acquires the input keyword and transmits the acquired keyword to the server device 1 (step S3).

After that, the search processing unit 31a determines whether or not the company information transmitted as the search result from the server device 1 is received in response to the transmission of the keyword (step S4). When the company information is not received (S4: NO), the search processing unit 31a waits until the company information is received. When the company information is received (S4: YES), the search processing unit 31a displays the received company information as a search result on the display unit 34 (step S5), and ends the process.

FIG. 9 is a flowchart showing the procedure of the search process performed by the server device 1 according to the present embodiment. The search processing unit 11a of the processing unit 11 of the server device 1 according to the present embodiment determines whether or not a search keyword has been received from the terminal device 3 (step S11). When the keyword is not received (S11: NO), the search processing unit 11a waits until the keyword is received from the terminal device 3. When the keyword is received (S11: YES), the search processing unit 11a inputs the received keyword into the learning model 12b of the storage unit 12 (step S12). The search processing unit 11a acquires the company label output by the learning model 12b in response to the input of the keyword (step S13). The search processing unit 11a reads out the company information from the company DB 12c of the storage unit 12 based on the acquired company label (step S14). The search processing unit 11a transmits the read company information to the terminal device 3 from which the keyword is transmitted (step S15), and returns the processing to step S11.

<Annotation processing>
In the information processing system according to the present embodiment, the learning model 12b of the server device 1 is periodically relearned in order to improve the search accuracy. In order to generate the teacher data used for this re-learning, the server device 1 requests the user who uses the search service to perform the work of associating the company with the keywords related to the company, that is, the work of annotation. Further, the server device 1 grants the user who has performed the annotation work the right to use the search service free of charge for a predetermined period as a privilege. As a result, the information processing system can encourage the user to perform the annotation work, create more teacher data, perform the re-learning process of the learning model 12b, and improve the accuracy of the search service using the learning model 12b. it can.

The server device 1 manages the period during which the search service can be used free of charge for each user. Information stored as a "free expiration date" in the user DB 12d of the storage unit 12 is used for this management. The server device 1 selects, for example, a user who has reached a predetermined number of days (for example, two weeks) until the free deadline from the user DB 12d, and transmits a request for performing annotation work to this user. At this time, the server device 1 selects the company to be annotated from the plurality of companies registered in the company DB 12c, selects a plurality of keyword candidates associated with the company, and selects the company and the plurality of candidate keywords. It is sent to the user's terminal device 3 to request annotation work.

The company to be annotated by the server device 1 can be selected by, for example, the following methods (1) to (3). The server device 1 may adopt any one of these methods, a plurality of methods may be used in combination, or a method other than these may be adopted.
(1) Selection based on the number of views of company information (2) Selection based on the number of annotations performed (3) Selection based on attribute information

(1) Selection based on the number of views of company information In the search service according to this embodiment, the user uses the service for the purpose of obtaining company information. Companies with a large number of views of corporate information are popular companies that are needed by users, and there is a high possibility that many users will continue to view them in the future. By preferentially targeting such companies as annotation targets and improving search accuracy, it can be expected to provide better search services. For example, the server device 1 counts the number of views for each company registered in the company information DB 12c, and ranks the number of views in a predetermined period such as one week or one month. The server device 1 weights the selection probability of the company according to the order of the number of views, that is, weights the company so that the higher the order, the higher the selection probability, and annotates from all the companies registered in the company information DB 12c. Select the target company.

(2) Selection based on the number of annotations performed The more teacher data for the re-learning process, the better the search accuracy can be expected, and the larger the number of annotations performed by a company, the better the search accuracy for this company. If there is a variation in the number of annotations, there is a possibility that the search accuracy will differ between companies, but this can be avoided or reduced by preferentially selecting companies with a small number of annotations as annotation targets. You can expect to do it. For example, the server device 1 counts the number of annotations executed for each company registered in the company information DB 12c, and ranks the number of annotations implemented in a predetermined period such as one week or one month. The server device 1 weights the selection probability of the company according to the order of the number of annotations, that is, the company with the smaller number of annotations has a higher selection probability, and among all the companies registered in the company information DB 12c. Select the company to be annotated from.

(3) Selection Based on Attribute Information In the present embodiment, the server device 1 stores the company attribute information of each company in the company information DB 12c and the user attribute information of each user in the user DB 12d. For example, when focusing on the industry included in the company attribute information and the user attribute information, the user can expect to carry out highly reliable annotation for a company in an industry close to the industry of his / her occupation. Also, for example, when focusing on the location included in the company attribute information and the address included in the user attribute information, the user trusts the company located near the place where he / she lives or the place where the company he / she works for. It can be expected that highly relevant annotations will be implemented. The server device 1 compares the specific company attribute information included in the company information stored in the company information DB 12c with the specific user attribute information about the user stored in the user DB 12d, and requests the work of annotation. A company that has company attribute information that satisfies a predetermined condition for the user attribute information is selected as the company to be annotated. The company attribute information and user attribute information used for selecting a company are not limited to the above-mentioned industry and location, and various types of information can be adopted. Based on the company attribute information and the user attribute information, the server device 1 may select, for example, the company of the business partner (supplier or sales destination) of the company in which the user works, or for example, the company in which the user works. You may select a competing company or a company that handles similar products.

Further, when selecting a keyword candidate associated with a company in the annotation work, the server device 1 may use, for example, a word extracted from the homepage of the company as a candidate keyword, or, for example, a set of words prepared in advance. A word randomly selected from the list may be used as a candidate keyword. A group of words can be prepared in advance by storing, for example, a word input as a keyword by a user who uses a search service in the server device 1.

The company to be annotated together with the request for annotation from the server device 1 and the terminal device 3 given the candidate of the keyword corresponding to this company are the annotation screens for the user to perform the annotation work based on the information. Is displayed on the display unit 34. FIG. 10 is a schematic diagram showing an example of the annotation screen. On the annotation screen displayed by the terminal device 3 according to the present embodiment, the message "Please select / enter a keyword related to X Co., Ltd." is displayed at the top. This message indicates that the company to be annotated is "X Co., Ltd.".

The terminal device 3 displays buttons labeled with keywords arranged in a matrix below this message. In the illustrated example, "AI", "IoT", "blockchain", "5G", "smart grid", "quantum computing", "restaurant", "wholesale", "nursing care", "transportation" , Twelve buttons labeled "Insurance" and "Medical" are arranged in a matrix of 4 rows x 3 columns. The terminal device 3 accepts the selection of the keyword associated with the company by accepting the touch operation or the click operation for each button. In the illustrated example, the selection of the keywords "AI" and "nursing care" is indicated by hatching the buttons.

Further, the terminal device 3 displays a character string of "arbitrary input" and a text box for inputting the character string side by side below the plurality of buttons. The user can input an arbitrary character string in this text box by using the character input function of the terminal device 3. The terminal device 3 accepts the character string input in the text box as a keyword associated with the company to be annotated. In the illustrated example, the keyword "robot" is entered in the text box.

Further, the terminal device 3 displays a button labeled "Back" and a button labeled "Send" side by side below the text box. The "Back" button accepts an operation of interrupting the annotation work and returning to the previous display state, for example, the display state of the menu screen or the search screen. The "send" button accepts an operation of sending the result of the annotation work by the user to the server device 1. When the operation for the "send" button is performed, the terminal device 3 transmits the annotation result information including the company to be annotated and the keyword associated with the company by the user to the server device 1. In the illustrated example, the annotation result in which the three keywords "AI", "nursing care", and "robot" are associated with "X Co., Ltd." is transmitted to the server device 1.

The server device 1 that has received the annotation result from the terminal device 3 stores the received information in the annotation information DB 12e of the storage unit 12. The server device 1 uses the information accumulated in the annotation information DB 12e to generate teacher data for the re-learning process of the learning model 12b. The server device 1 can generate teacher data and perform re-learning processing of the learning model 12b using the teacher data at a cycle of, for example, one week or one month.

However, the result of the annotation performed by the user is not always correct, and when the learning model 12b is relearned using the teacher data in which the correspondence (relationship) between the company and the keyword contains an error. May reduce search accuracy. Therefore, in the information processing system according to the present embodiment, in order to improve the reliability of the annotation result, at least one of the following processes (1) to (3) is executed, and the correspondence between the company and the keyword is obtained. May be determined.
(1) Two-step annotation (2) Majority decision of multiple users (3) Evaluation of user performance

(1) The two-stage annotation server device 1 requests, for example, the first user to perform the above-mentioned annotation work, acquires the result, and then determines whether the result of this annotation is correct or not for the second user. Request work. The server device 1 stores the result of the annotation determined to be valid by the second user in the annotation information DB 12e and uses it as the teacher data of the learning model 12b. Further, the server device 1 may give a privilege to both the first user who has performed the annotation work and the second user who has performed the work of determining the correctness of the annotation result.

(2) Majority decision of a plurality of users The server device 1 generates information for annotation in which one company is associated with a plurality of candidate keywords, and sends the same information to a plurality of users to perform annotation work. Make an implementation request. The server device 1 compares the results of a plurality of annotations acquired from the plurality of users, and for example, a keyword associated with more than half of the users, a keyword associated with a predetermined number or more of users, or a keyword associated with the company. , Get the keywords etc. associated with the most users. The server device 1 stores the information in which the acquired one or more keywords are associated with this company in the annotation information DB 12e.

(3) User Performance Evaluation The server device 1 stores information on performance related to annotation work for each user registered in the user DB 12d. The actual information can be, for example, the number of annotations performed so far. Further, for example, when the above (1) or (2) is performed, the number of annotations that can be determined to be valid, the ratio of the number of valid annotations to the total number of annotations, and the like may be used as actual information. For example, the server device 1 may adopt only the result of the annotation of the user whose actual result exceeds the threshold value. Further, for example, when the server device 1 performs the above (1), the determination in the second stage may be omitted for the result of the annotation performed by the user whose actual result exceeds the threshold value. Further, for example, when the server device 1 performs the above (2), each user may be weighted according to the actual results, and the number of users associated with each keyword may be calculated. When calculating the number of users associated with each keyword for a company, the server device 1 can calculate the number of users for, for example, two users whose number of annotations exceeds the threshold value.

The server device 1 combines one or several of the above processes (1) to (3) and finally uses the result as the teacher data from the annotation results obtained from the terminal device 3. It is selected and stored in the annotation information DB 12e. Alternatively, the server device 1 may store all the annotation results acquired from the terminal device 3 in the annotation information DB 12e. In this case, the relearning process of the learning model 12b may be performed or at an appropriate timing before that. , The results of annotations used as teacher data may be selected by performing the above processes (1) to (3). The correspondence information of the company and the keyword selected in this way is used as the teacher data, and the re-learning process of the learning model 12b is performed. However, the server device 1 may perform the re-learning process using the results of all the annotations acquired from the terminal device 3 without performing such selection.

Further, the server device 1 gives a privilege to the user who has performed the annotation work. In the information processing system according to the present embodiment, the user is given the right to use the search service provided by the server device 1 free of charge for a predetermined period as a privilege. The server device 1 can give the above-mentioned privilege by extending the "free period" of the user DB 12d. The server device 1 may give a privilege to a user whose number of work of annotation exceeds a threshold, for example, or may determine a free period according to the number of work, for example. The server device 1 transmits a message notifying that the privilege has been granted to the terminal device 3 of the user who has granted the privilege. Upon receiving this message, the terminal device 3 notifies the user that the privilege has been granted by performing the annotation work.

FIG. 11 is a flowchart showing a procedure of annotation processing performed by the server device 1 according to the present embodiment. The annotation processing unit 11b of the processing unit 11 of the server device 1 according to the present embodiment determines whether or not the timing for requesting the annotation work has been reached for each user registered in the user DB 12d (step S31). Whether or not the timing for requesting the annotation work has been reached is determined by whether or not the predetermined number of days before the "free deadline" of the user DB 12d has been reached. When the request timing has not been reached (S31: NO), the annotation processing unit 11b waits until the timing for requesting the annotation work is reached.

When the timing for requesting the annotation work is reached (S31: YES), the annotation processing unit 11b generates the content of the annotation requested to the user (step S32). In the present embodiment, the content of the annotation includes, but is not limited to, the company to be annotated and a plurality of keywords associated with the company. The annotation processing unit 11b transmits the content of the generated annotation to the user's terminal device 3, thereby transmitting a request for executing the annotation work to the user (step S33).

The annotation processing unit 11b determines whether or not the annotation result has been received from the terminal device 3 of the user who has transmitted the request for performing the annotation work (step S34). In the information processing system according to the present embodiment, it is possible for the user not to accept the request of the server device 1, and when the annotation result is not accepted (S34: NO), the annotation processing unit 11b processes. To finish.

When the result of annotation by the user is received from the terminal device 3 (S34: YES), the annotation processing unit 11b transmits the result of the received annotation, that is, the information associated with the company and the keyword, to the annotation information DB 12e of the storage unit 12. Store (step S35). The privilege giving unit 11c of the processing unit 11 grants the user who has performed the annotation work the right to use the search service free of charge for a predetermined period as a privilege (step S36), and ends the process. In this flowchart, processing for improving the reliability of annotation results, that is, (1) two-step annotation, (2) majority decision of multiple users, and (3) user performance evaluation processing is performed. Absent. These processes can be performed, for example, before and after step S35 of this flowchart.

FIG. 12 is a flowchart showing a procedure of annotation processing performed by the terminal device 3 according to the present embodiment. The annotation processing unit 31b of the processing unit 31 of the terminal device 3 according to the present embodiment determines whether or not the request for execution of the annotation work has been received from the server device 1 (step S51). When the execution request of the annotation work is not accepted (S51: NO), the annotation processing unit 31b waits until the execution request is accepted.

When the request for performing the annotation work is received (S51: YES), the annotation processing unit 31b informs the company to be annotated and this company based on the information about the content of the annotation transmitted from the server device 1. An annotation screen (see FIG. 10) showing the keywords that are candidates for association is displayed on the display unit 34 (step S52). The annotation processing unit 31b accepts the annotation work by the user by accepting the selection or input of the keyword on the annotation screen (step S53). The annotation processing unit 31b transmits the result of the annotation work by the user, that is, the information regarding the correspondence between the company and the keyword to the server device 1 (step S54).

The annotation processing unit 31b determines whether or not the notification that the privilege has been given to the user has been received from the server device 1 (step S55). For example, when the work of a predetermined number or more of annotations is a condition for granting the privilege, the privilege may not be granted only by the user performing the work of one annotation. When the privilege is not given in this way (S55: NO), the annotation processing unit 31b ends the process. On the other hand, when the privilege is given to the user (S55: YES), the annotation processing unit 31b displays, for example, a message or the like on the display unit 34 to notify the user that the privilege has been given (step S56). ), End the process.

<Other benefits>
In the present embodiment, as a privilege given to the user by the server device 1, the right to use the search service free of charge for a predetermined period has been described as an example, but the privilege may be other than this. Good. For example, the server device 1 may provide a part of the functions of the service for a fee and grant the user the right to use this function free of charge as a privilege. For example, in the server device 1, the search service is provided to all users free of charge, and a difference may be provided between the paid member and the free member regarding the quantity and quality of the company information displayed as the search result. In this case, the paid member The same right as the above may be given to the user as a privilege free of charge. Further, for example, the server device 1 may have a function of displaying an advertisement on a search screen, a search result display screen, or the like, and in this case, the right to distribute the advertisement for free may be given to the user as a privilege. Good. Further, the server device 1 may display a plurality of company information on the search result display screen, and in this case, the user may be given the right to display the company information at a higher level as a privilege. The server device 1 may give various benefits other than these to the user who has performed the annotation work.

<Summary>
In the information processing system according to the present embodiment having the above configuration, the server device 1 provides a search service that accepts input of a keyword for search from a user and outputs information about one or more companies corresponding to the keyword. provide. The server device 1 sends a request for performing the annotation work associated with the keyword and the company to the user, acquires the information associated with the keyword and the company from the terminal device 3 as a result of the annotation work from the user, and also performs the annotation work. The privilege is given to the user who carried out the above. As a result, the information processing system according to the present embodiment can prompt the user to perform the annotation work, collect more annotation results, and use the information processing system for improving the search accuracy and the like. By requesting the user to perform annotation work in this way, for example, data for learning can be generated without going through the provider of the search service, and as a result, improvement in search accuracy can be expected.

Further, the information processing system according to the present embodiment grants the user the right to use the search service free of charge for a predetermined period as a privilege. As a result, it can be expected that users who use the search service will be more effectively encouraged to carry out the annotation work.

Further, the information processing system according to the present embodiment sends a request for performing annotation work to the user before the period during which the search service can be used free of charge (free period) elapses. As a result, the user can use the search service without interruption of the free period by performing the annotation work.

Further, the information processing system according to the present embodiment sends an annotation work execution request to a plurality of users to one company, acquires the results of the annotation work from the plurality of users, and obtains a plurality of acquired results. Based on the results, the keywords used as teacher data and the correspondence between companies are determined. For example, a predetermined number or more of users can extract a keyword associated with a company, and associate this keyword with the company to obtain teacher data. Keywords associated with this company by less than a predetermined number of users are judged to be unreliable as keywords associated with this company, and are not used as teacher data. As a result, the learning model 12b can be relearned using the highly reliable annotation results, and more reliable search accuracy can be expected to be improved.

Further, in the information processing system according to the present embodiment, the server device 1 stores the work results of the users, and based on the results of annotations by a plurality of users and the results of the users who performed the annotation work for each result. Determine the keywords used as teacher data and the correspondence between companies. For example, a user who has performed more than a predetermined number of annotations so far determines that highly reliable annotation can be performed, and when counting the number of users who have assigned keywords to a company as described above, the number of users is counted. This user can be weighted (for example, this user is counted as two people) to determine the keyword associated with the company. Further, the keywords associated with the company by the user with a higher track record in the annotation work may be adopted as the teacher data regardless of whether or not the other users have associated them. As a result, the re-learning process can be performed using the result of the annotation with higher reliability, and more reliable improvement of the search accuracy can be expected.

Further, the information processing system according to the present embodiment determines a target company for requesting the user to perform the annotation work based on the number of times the company information is viewed in the search service or the number of times the user performs the annotation work. As a result, for example, it is expected to improve the search accuracy for companies that have a large number of views and are required by users, and for example, the search accuracy for companies that have a small number of annotation operations and do not have sufficient teacher data can be improved. You can expect it.

Further, the information processing system according to the present embodiment determines a company that requests the user to perform annotation work based on the user attribute information and the company attribute information. For example, by requesting annotation work for a company in the same industry or region as the user, it can be expected that highly reliable annotation results can be obtained.

Further, the information processing system according to the present embodiment presents a plurality of candidate keywords to be associated with one company to the user, and accepts the selection of one or a plurality of candidate keywords from the presented plurality of candidate keywords. Get the result of the annotation work by the user. As a result, the user can expect to easily carry out the annotation work.

In the present embodiment, the search target of the search service is a company, but the present invention is not limited to this, and the server device 1 may provide a search service that handles various search targets other than the company.

The embodiments disclosed this time should be considered as exemplary in all respects and not restrictive. The scope of the present invention is indicated by the scope of claims, not the above-mentioned meaning, and is intended to include all modifications within the meaning and scope equivalent to the scope of claims.

1 Server device 3 Terminal device 11 Processing unit 11a Search processing unit 11b Annotation processing unit 11c Bonus granting unit 11d Learning processing unit 12 Storage unit 12a Server program 12b Learning model 12c Corporate information DB
12d user DB
12e Annotation information DB
13 Communication unit 31 Processing unit 31a Search processing unit 31b Annotation processing unit 32 Storage unit 32a Program 33 Communication unit 34 Display unit 35 Operation unit 98,99 Recording medium

Claims (11)

Information processing device
A request for performing work of associating a search keyword and a search target related to the search service is sent to the user of the search service.
As a result of the work, the information associated with the keyword and the search target is acquired from the user, and the information is obtained.
Granting the user who performed the work the right to use the search service for a predetermined period of time.
Information processing method. The information processing device transmits a request for performing the work to the user before the predetermined period elapses.
The information processing method according to claim 1. Information processing device
Memorize user attribute information
Memorize the attribute information of the company to be searched,
Based on the memorized both attribute information, determine the company to request the work to the user,
A request for performing work of associating a search keyword and a search target related to the search service is sent to the user of the search service.
As a result of the work, the information associated with the keyword and the search target is acquired from the user, and the information is obtained.
Granting benefits to users who have performed the above work,
Information processing method. The information processing device
Send the work execution request to multiple users for one search target,
Obtaining the results of the work from the plurality of users
The relationship between the keyword and the search target is determined based on the obtained plurality of results.
The information processing method according to any one of claims 1 to 3. The information processing device
Memorize the work record of the user and
The relationship between the keyword and the search target is determined based on the acquired plurality of results and the results of the user who performed the work of each result.
The information processing method according to claim 4. The information processing device determines a search target for which the user is requested to perform the work, based on the number of times the information is viewed in the search service or the number of times the user performs the work.
The information processing method according to any one of claims 1 to 5. The information processing device
Presenting to the user multiple candidate keywords that correspond to one search target,
From the presented plurality of candidate keywords, the selection of one or a plurality of keywords is acquired from the user as a result of the work.
The information processing method according to any one of claims 1 to 6. On the computer
A request for performing work of associating a search keyword and a search target related to the search service is sent to the user of the search service.
As a result of the work, the information associated with the keyword and the search target is acquired from the user, and the information is obtained.
Granting the user who performed the work the right to use the search service for a predetermined period of time.
A computer program that executes processing. On the computer
Memorize user attribute information
Memorize the attribute information of the company to be searched,
Based on the memorized both attribute information, determine the company to request the work to the user,
A request for performing work of associating a search keyword and a search target related to the search service is sent to the user of the search service.
As a result of the work, the information associated with the keyword and the search target is acquired from the user, and the information is obtained.
Granting benefits to users who have performed the above work,
A computer program that executes processing. A work request transmission unit that transmits a work request for associating a search keyword and a search target related to the search service to the user of the search service.
A work result acquisition unit that acquires information associated with a keyword and a search target as a result of the work from the user.
An information processing device including a privilege granting unit that grants a user who has performed the work the right to use the search service for a predetermined period of time. A storage unit that stores the attribute information of the user and the attribute information of the company to be searched,
Based on the memorized both attribute information, the decision department that decides the company to request the work to the user,
A work request transmission unit that transmits a work request for associating a search keyword and a search target related to the search service to the user of the search service.
A work result acquisition unit that acquires information associated with a keyword and a search target as a result of the work from the user.
With the privilege granting department that grants benefits to the user who performed the above work
Information processing device.

Images