Information processing device, information processing method, and information processing program

Abstract

To automatically build a dictionary for unambiguous domain-specific words.SOLUTION: An information processing device according to the present application comprises: a learning unit that uses unambiguous proper nouns that are uniquely used with an intention of indicating a specific object and character strings that are related to the unambiguous proper nouns to build a model that estimates whether an input proper noun is an unambiguous proper noun through learning; a detection unit that inputs a proper noun to the learnt model, and detects the unambiguous proper noun; and a dictionary generation unit that automatically generates an unambiguous proper noun dictionary on the basis of the detected unambiguous proper nouns.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] Techniques for automatically generating dictionaries are disclosed.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the above prior art only automatically generates a care dictionary used for input support for care records. Domain-specific words indicating proper nouns in a specific domain (specific field / area) include ambiguous domain-specific words that are used not only for the meaning of a base name representing a point on a map but also for other meanings, and non-ambiguous domain-specific words that are only used for the meaning of a base name representing a point on a map. The prior art has not been able to automatically construct a dictionary that distinguishes between ambiguous domain-specific words and non-ambiguous domain-specific words.

[0005] The present application has been made in view of the above, and an object thereof is to automatically construct a dictionary of non-ambiguous domain-specific words.

Means for Solving the Problems

[0006] The information processing device according to the present application comprises: a learning unit that uses non-ambiguous proper nouns used uniquely with the intention of indicating a specific object and strings associated with the non-ambiguous proper nouns to build a model by learning that estimates whether an input proper noun is a non-ambiguous proper noun based on the input proper noun and the strings associated with the proper nouns; a detection unit that uses the learned model to detect non-ambiguous proper nouns based on the input proper noun and the strings associated with the proper nouns; and a dictionary generation unit that automatically generates a dictionary of non-ambiguous proper nouns based on the detected non-ambiguous proper nouns. The strings associated with the aforementioned proper nouns are the strings entered together with the aforementioned proper nouns in the search. It is characterized by the following: [Effects of the Invention]

[0007] According to one embodiment, a dictionary of non-ambiguous domain-specific terms is automatically constructed. It is possible. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 is an explanatory diagram showing an overview of the information processing method according to the embodiment. [Figure 2] Figure 2 is an explanatory diagram illustrating the overview of its application to a named entity recognition system. [Figure 3] Figure 3 is an explanatory diagram illustrating the overview of its application to a document classification system. [Figure 4] Figure 4 shows an example of the configuration of an information processing system according to the embodiment. [Figure 5] Figure 5 shows an example of the configuration of a terminal device according to this embodiment. [Figure 6] Figure 6 shows an example of the configuration of a server device according to the embodiment. [Figure 7] Figure 7 shows an example of a user information database. [Figure 8] Figure 8 shows an example of a historical information database. [Figure 9] Figure 9 shows an example of a non-ambiguous information database. [Figure 10]Figure 10 is a flowchart showing the processing procedure according to the embodiment. [Figure 11] Figure 11 shows an example of a hardware configuration. [Modes for carrying out the invention]

[0009] The following describes in detail, with reference to the drawings, embodiments for implementing the information processing device, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing device, information processing method, and information processing program according to the present application. Furthermore, the same parts are denoted by the same reference numerals in the following embodiments, and redundant descriptions are omitted.

[0010] [1. Overview of Information Processing Methods] First, with reference to Figure 1, an overview of the information processing method performed by the information processing device according to the embodiment will be described. Figure 1 is an explanatory diagram showing an overview of the information processing method according to the embodiment. In Figure 1, the case of automatically constructing a dictionary of non-ambiguous domain-specific words will be used as an example.

[0011] As shown in Figure 1, the information processing system 1 includes a terminal device 10 and a server device 100. The terminal device 10 and the server device 100 are connected to each other via a network N (see Figure 4) by wire or wireless means so that they can communicate with each other. In this embodiment, the terminal device 10 cooperates with the server device 100.

[0012] The terminal device 10 is a smart device such as a smartphone or a tablet terminal used by the user U, and is a portable terminal device capable of communicating with an arbitrary server device via a wireless communication network such as 5G (Generation) or LTE (Long Term Evolution). Further, the terminal device 10 has a screen such as a liquid crystal display and has a screen having a touch panel function, and receives various operations on display data such as content, such as a tap operation, a slide operation, and a scroll operation, from the user U using a finger or a stylus. Note that an operation performed on the area of the screen where the content is displayed may be regarded as an operation on the content. Further, the terminal device 10 may be not only a smart device but also an information processing device such as a desktop PC (Personal Computer) or a notebook PC.

[0013] The server device 100 is an information processing device that cooperates with the terminal device 10 of each user U and provides an API (Application Programming Interface) service and various data for various applications (hereinafter referred to as apps) and the like to the terminal device 10 of each user U, and is realized by a computer, a cloud system, or the like.

[0014] Further, the server device 100 may be an information processing device that provides some kind of web service online to the terminal device 10 of each user U. For example, as a web service, the server device 100 may provide services such as internet connection, search service, SNS (Social Networking Service), electronic commerce (EC: Electronic Commerce), electronic payment, online game, online banking, online trading, accommodation / ticket reservation, video / music distribution, news, map, route search, route guidance, route information, operation information, weather forecast, and the like. In reality, the server device 100 may cooperate with various servers that provide the above web services and mediate the web service, or may be in charge of the processing of the web service.

[0015] The server device 100 can acquire user information regarding the user U. For example, the server device 100 acquires information regarding the attributes of the user U, such as the gender, age, and residential area of the user U. Then, the server device 100 stores and manages the information regarding the attributes of the user U together with the identification information (such as user ID) indicating the user U.

[0016] In addition, the server device 100 acquires various types of history information (log data) indicating the actions of the user U from the terminal device 10 of the user U or from various servers, etc. based on the user ID, etc. For example, the server device 100 acquires a location history, which is a history of the location and time of the user U, from the terminal device 10. Also, the server device 100 acquires a search history, which is a history of the search queries input by the user U, from a search server (search engine). Further, the server device 100 acquires a browsing history, which is a history of the content browsed by the user U, from a content server. Additionally, the server device 100 acquires a purchase history (settlement history), which is a history of the user U's product purchases and settlement processes, from an e-commerce server or a settlement processing server. Moreover, the server device 100 may acquire a posting history or a sales history, which is a history of the user U's postings on a marketplace, from an e-commerce server or a settlement processing server. Also, the server device 100 acquires a posting history, which is a history of the user U's postings, from a posting server or an SNS server that provides a word-of-mouth posting service. Note that each of the above various servers, etc. may be the server device 100 itself. That is, the server device 100 may function as each of the above various servers, etc.

[0017] [1-1. Automatic generation of non-ambiguous domain-specific dictionary] A method for constructing a non-ambiguous domain-specific dictionary that utilizes the co-occurrence information of search queries will be described. A non-ambiguous domain-specific word is a word (proper noun) that has no ambiguity in a specific domain (specific field / area) and refers to one concept, and can be utilized in various natural language processing (NLP: Natural Language Processing) systems.

[0018] A non-ambiguous domain-specific dictionary is useful in building named entity identifiers for a given domain, especially when you want to quickly create a high-precision extractor or when the context of target terms, such as tweets or search queries, is limited and resolving ambiguity is difficult. However, since there are countless non-ambiguous domain-specific words and new words are constantly emerging, building such a dictionary manually is difficult. Therefore, there is a need for automated construction of non-ambiguous domain-specific dictionaries.

[0019] In this embodiment, a dictionary of non-ambiguous domain-specific terms (non-ambiguous landmark terms) targeting location names is automatically constructed. For example, words that are the names of real facilities but are also used as general words (e.g., "daruma," "tulip") and words that are location names and proper nouns but can be used for purposes other than landmarks (e.g., "Koshien") fall under the category of ambiguous domain-specific terms (ambiguous landmark terms). In contrast, words that rarely appear in any sense other than location names representing a point on a map (e.g., "Kioi Tower") fall under the category of non-ambiguous domain-specific terms (non-ambiguous landmark terms).

[0020] Furthermore, the tendency of co-occurrence queries in search queries differs between ambiguous domain-specific terms and non-ambiguous domain-specific terms. For example, ambiguous domain-specific terms co-occur with various words even outside of landmark intent (e.g., "Koshien directions", "Koshien breaking news", "Koshien winning school"). In contrast, non-ambiguous domain-specific terms co-occur with specific words in landmark intent (e.g., "Kioi Tower directions", "Kioi Tower restaurants", "Kioi Tower access"). Therefore, a machine learning model is constructed that utilizes the co-occurrence information of search queries. In this embodiment, a model (binary classifier) ​​is constructed that takes a search query and performs binary classification of whether or not it is a non-ambiguous domain-specific term. For example, when the word "Kioi Tower" is input, a model (binary classifier) ​​is constructed that classifies it as a non-ambiguous domain-specific term. Alternatively, if you input the term "Kioi Tower" along with co-occurring words such as "directions," "access," or "restaurant," a model (binary classifier) ​​will be constructed that classifies them as non-ambiguous domain-specific words (non-ambiguous domain-specific words).

[0021] For example, as shown in Figure 1, the server device 100 acquires non-ambiguous proper nouns (non-ambiguous domain-specific words), which are proper nouns that are used uniquely with the intention of indicating a specific object (such as a location name), and ambiguous proper nouns (ambiguous domain-specific words), which are proper nouns that can be used not only with the intention of indicating a specific object but also with other intentions (step S1).

[0022] Next, the server device 100 collects search queries entered with non-ambiguous proper nouns (non-ambiguous co-occurring word queries) and search queries entered with ambiguous proper nouns (ambiguous co-occurring word queries) (step S2).

[0023] Next, the server device 100 constructs a training dataset using pairs of non-ambiguous proper nouns and non-ambiguous co-occurring word queries, and pairs of ambiguous proper nouns and ambiguous co-occurring word queries (step S3).

[0024] In practice, the server device 100 may collect data from logs of search servers, etc., specifically data of pairs of non-ambiguous proper nouns and non-ambiguous co-occurring word queries, and data of pairs of ambiguous proper nouns and ambiguous co-occurring word queries.

[0025] Next, the server device 100 constructs a model (binary classifier) ​​through learning using a dataset of pairs of unambiguous proper nouns and unambiguous co-occurring word queries, and a dataset of pairs of ambiguous proper nouns and ambiguous co-occurring word queries (step S4).

[0026] Furthermore, learning may also be performed using Transformers. For example, learning may be performed using BERT (Bidirectional Encoder Representations from Transformers) as shown below.

[0027] (1) Pre-learning The server device 100 performs unsupervised learning without using labels during pre-training. However, the server device 100 does not necessarily need to perform pre-training unless it is using a pre-trained large-scale model such as BERT. In other words, pre-training is essential for training large-scale models such as BERT, but not essential for training other models.

[0028] (2) This learning (re-learning) During this training phase, the server device 100 performs supervised learning using labels. Examples of this training include transfer learning and fine-tuning. For example, the server device 100 trains a binary classification model using training data that includes proper nouns and labels indicating whether they are unambiguous or ambiguous. This training is always required.

[0029] (A) Proposed method 1 Server device 100 uses search query text for pre-training (instead of the usual use of general text). For example, server device 100 performs unsupervised learning without labels using search query text during pre-training. This unsupervised learning method is similar to the pre-training method of BERT, which uses a pre-trained model, in that tokens (≒words) in the text are randomly hidden (masked), and the model is asked to guess the hidden (masked) parts. This learning is unsupervised learning that does not require the use of manually constructed correct labels, and does not perform supervised learning such as classifying whether something is ambiguous or unambiguous. By performing this unsupervised learning using search query text instead of general text, it is possible to implicitly embed information about how domain-specific words co-occur in search queries into the machine learning model beforehand. This improves the classification performance after the main training. In addition, during inference, by inputting a single proper noun (a proper noun whose status as unambiguous or ambiguous is unknown, such as a candidate facility name), it is possible to classify whether it is an unambiguous proper noun or not.

[0030] (B) Proposed method 2 During this training phase, the server device 100 learns using pairs of proper nouns and search queries (co-occurring words) as input data (instead of using individual proper nouns as input data as is typical). For example, the server device 100 takes a pair of an unambiguous proper noun and an unambiguous co-occurring word query, or an ambiguous proper noun and an ambiguous co-occurring word query, as input and constructs a model that estimates whether it is an unambiguous or ambiguous proper noun. Models of any architecture can be used. In this case, during inference, the server device 100 inputs the proper noun into the model and classifies it as either an unambiguous or ambiguous proper noun. This is because the model is trained to estimate co-occurring word queries that are likely to be input together with the input proper noun, and then considers the estimated co-occurring word queries to determine whether it is an unambiguous or ambiguous proper noun. Alternatively, the server device 100 may input the proper noun and the co-occurring word query into the model and classify them as either an unambiguous or ambiguous proper noun.

[0031] In this case, the server device 100 may label the dataset containing pairs of unambiguous proper nouns and unambiguous co-occurring word queries as "unambiguous" and the dataset containing pairs of ambiguous proper nouns and ambiguous co-occurring word queries as "ambiguous". The server device 100 may also perform labeling by crowdsourcing. The labels may be "Yes" to indicate that it is an unambiguous proper noun and "No" to indicate that it is an ambiguous proper noun. In other words, any label that can distinguish between "unambiguous" and "ambiguous" is acceptable.

[0032] Next, the server device 100 uses a trained model (binary classifier) ​​to detect (automatically extract) unambiguous proper nouns that can identify specific landmarks (step S5).

[0033] For example, the server device 100 may input proper nouns into a model (binary classifier) ​​and perform binary classification to determine whether they are unambiguous proper nouns or not. Unambiguous proper nouns have different co-occurrence query tendencies than ambiguous proper nouns. In this embodiment, the server device 100 inputs proper nouns into a model (binary classifier) ​​and classifies them into either unambiguous proper nouns or ambiguous proper nouns. Alternatively, the server device 100 may input pairs of proper nouns and co-occurrence queries into a model (binary classifier) ​​and perform binary classification to determine whether they are unambiguous proper nouns or not.

[0034] Next, the server device 100 automatically constructs (automatically generates) a dictionary of non-ambiguous proper nouns (a dictionary of non-ambiguous domain-specific words) based on the detected non-ambiguous proper nouns (step S6).

[0035] In this embodiment, a landmark (location information) domain is described as an example of a specific domain, but the same applies to other specific domains. Examples of other specific domains include shopping, medical, and recipes.

[0036] Thus, in this embodiment, the server device 100 learns a model (binary classifier) ​​that estimates whether an input proper noun (keyword, etc.) is an unambiguous proper noun or an ambiguous proper noun, using unambiguous proper nouns that are uniquely used with the intention of indicating a specific object (such as a location name), ambiguous proper nouns that can be used not only with the intention of indicating a specific object but also with other intentions, and strings (such as co-occurring words) that are related to unambiguous or ambiguous proper nouns.

[0037] Furthermore, proper nouns may be extracted from readily available lists of entity names (publicly available web pages, databases, etc.). Proper nouns and search queries may also be strings appearing in text documents. Moreover, proper nouns and search queries may be strings extracted from image data using image recognition, or strings extracted from audio data using speech recognition. In addition, proper nouns are not limited to domain-specific terms of landmark domains, but may also be proper nouns from other fields such as medicine (vague disease names, drug names, medical device names, etc.) and recipes (vague dish names, food names, seasoning names, etc.).

[0038] Relevant strings could be, for example, search queries entered together with proper nouns, or words that frequently appear together with proper nouns within papers or content.

[0039] The server device 100 then uses a model (binary classifier) ​​to detect (automatically extract) unambiguous proper nouns and builds a dictionary of unambiguous proper nouns. The server device 100 can also input the search query to be judged into a model (binary classifier) ​​that estimates whether the input proper noun is an unambiguous or ambiguous proper noun, estimate whether it is an ambiguous or unambiguous proper noun, and may adjust the search results or suggest keywords to input along with it according to the estimation result.

[0040] Furthermore, as an example of application, the server device 100 can apply the above model (binary classifier) ​​and unambiguous proper noun dictionary to existing systems. Figure 2 is an explanatory diagram showing an overview of application to a named entity recognition system. Figure 3 is an explanatory diagram showing an overview of application to a document classification system.

[0041] For example, as shown in Figure 2(A), the server device 100 can quickly construct a highly accurate and high-speed named entity recognition system by incorporating an unambiguous proper noun dictionary into the named entity recognition system. This named entity recognition system can also handle cases with limited context.

[0042] Furthermore, as shown in Figure 2(B), the server device 100 may also add the above model (binary classifier) ​​as a filter function to the existing named entity recognition system. Performance can be improved simply by adding the model (binary classifier) ​​without requiring any changes to the existing named entity recognition system itself.

[0043] Furthermore, as shown in Figure 3, the server device 100 may add the above model (binary classifier) ​​as a filtering function to remove ambiguous features after extracting features in the document classification system, or it may remove ambiguous features using a non-ambiguous proper noun dictionary.

[0044] Furthermore, although not shown in the diagram, the server device 100 may also use a model (binary classifier) ​​and an unambiguous proper noun dictionary to determine the query intent of shopping searches. For example, the server device 100 may use a model (binary classifier) ​​and an unambiguous proper noun dictionary to detect unambiguous product names and use only unambiguous product names for determination.

[0045] [2. Example of an information processing system configuration] Next, the configuration of the information processing system 1, which includes the server device 100 according to the embodiment, will be described using Figure 4. Figure 4 is a diagram showing an example of the configuration of the information processing system 1 according to the embodiment. As shown in Figure 4, the information processing system 1 according to the embodiment includes a terminal device 10 and a server device 100. These various devices are connected to each other via a network N, either by wire or wireless communication. The network N is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network) such as the Internet.

[0046] Furthermore, the number of devices included in the information processing system 1 shown in Figure 4 is not limited to those illustrated. For example, in Figure 4, only one terminal device 10 is shown for the sake of illustration, but this is merely an example and not limiting; there may be two or more.

[0047] Terminal device 10 is an information processing device used by user U. For example, terminal device 10 may be a smart device such as a smartphone or tablet, a mobile phone such as a feature phone, a PC (Personal Computer), a PDA (Personal Digital Assistant), a game console or AV equipment with communication functions, an information appliance or digital appliance, a car navigation system, a wearable device such as a smartwatch or head-mounted display, or smart glasses. Alternatively, terminal device 10 may be a house or building compatible with the Internet of Things (IoT), a car, a home appliance, an electronic device, etc.

[0048] Furthermore, the terminal device 10 can connect to the network N via wireless communication networks such as LTE (Long Term Evolution), 4G (4th Generation), and 5G (5th Generation), or via short-range wireless communication such as Bluetooth (registered trademark) and Wi-Fi (Local Area Network), and communicate with the server device 100.

[0049] The server device 100 is, for example, a computer such as a PC or blade server, or a mainframe or workstation. The server device 100 may also be implemented through cloud computing.

[0050] [3. Example of terminal device configuration] Next, the configuration of the terminal device 10 will be explained using Figure 5. Figure 5 is a diagram showing an example of the configuration of the terminal device 10. As shown in Figure 5, the terminal device 10 comprises a communication unit 11, a display unit 12, an input unit 13, a positioning unit 14, a sensor unit 20, a control unit 30 (controller), and a storage unit 40.

[0051] (Communications Section 11) The communication unit 11 is connected to the network N (see Figure 4) by wire or wireless connection and transmits and receives information to and from the server device 100 via the network N. For example, the communication unit 11 can be implemented using a NIC (Network Interface Card) or an antenna.

[0052] (Display section 12) The display unit 12 is a display device that displays various information such as location information. For example, the display unit 12 may be a liquid crystal display (LCD) or an organic electro-luminescent display (OLED). The display unit 12 may also be a touch panel display, but is not limited to this.

[0053] (Input section 13) The input unit 13 is an input device that receives various operations from the user U. For example, the input unit 13 has buttons for inputting characters, numbers, etc. The input unit 13 may also be an input / output port (I / O port) or a USB (Universal Serial Bus) port. If the display unit 12 is a touch panel display, a part of the display unit 12 functions as the input unit 13. The input unit 13 may also be a microphone that receives voice input from the user U. The microphone may be wireless.

[0054] (Positioning unit 14) The positioning unit 14 receives signals (radio waves) transmitted from GPS (Global Positioning System) satellites and, based on the received signals, acquires position information (e.g., latitude and longitude) indicating the current position of the terminal device 10. In other words, the positioning unit 14 determines the position of the terminal device 10. Note that GPS is just one example of a GNSS (Global Navigation Satellite System).

[0055] Furthermore, the positioning unit 14 can determine its position using various methods other than GPS. For example, the positioning unit 14 may use various communication functions of the terminal device 10 to determine its position as an auxiliary positioning means for position correction, etc., as described below.

[0056] (Wi-Fi positioning) For example, the positioning unit 14 determines the location of the terminal device 10 by utilizing the Wi-Fi® communication function of the terminal device 10 and the communication network provided by each telecommunications company. Specifically, the positioning unit 14 determines the location of the terminal device 10 by performing Wi-Fi communication, etc., and determining the distance to nearby base stations and access points.

[0057] (Beacon positioning) Furthermore, the positioning unit 14 may determine the location using the Bluetooth® function of the terminal device 10. For example, the positioning unit 14 determines the location of the terminal device 10 by connecting to a beacon transmitter connected via the Bluetooth® function.

[0058] (Geomagnetic positioning) Furthermore, the positioning unit 14 determines the position of the terminal device 10 based on the geomagnetic pattern of the structure, which has been measured in advance, and the geomagnetic sensor provided by the terminal device 10.

[0059] (RFID positioning) Furthermore, if, for example, the terminal device 10 is equipped with an RFID (Radio Frequency Identification) tag function equivalent to that of a contactless IC card used at a train station ticket gate or in a store, or if it is equipped with a function to read RFID tags, the location where it was used will be recorded along with the information on the payment or other transactions made by the terminal device 10. The positioning unit 14 may determine the location of the terminal device 10 by acquiring such information. Alternatively, the location may be determined by an optical sensor or infrared sensor equipped in the terminal device 10.

[0060] The positioning unit 14 may, if necessary, determine the position of the terminal device 10 using one or a combination of the positioning means described above.

[0061] (Sensor unit 20) The sensor unit 20 includes various sensors mounted on or connected to the terminal device 10. The connection can be wired or wireless. For example, the sensors may be detection devices other than the terminal device 10, such as wearable devices or wireless devices. In the example shown in Figure 5, the sensor unit 20 includes an acceleration sensor 21, a gyro sensor 22, a barometric pressure sensor 23, a temperature sensor 24, a sound sensor 25, a light sensor 26, a magnetic sensor 27, and an image sensor (camera) 28.

[0062] The sensors 21-28 described above are merely examples and not limiting. In other words, the sensor unit 20 may be configured to include some of the sensors 21-28, or it may include other sensors such as humidity sensors in addition to or instead of the sensors 21-28.

[0063] The acceleration sensor 21 is, for example, a 3-axis acceleration sensor and detects the physical movement of the terminal device 10, such as its direction of movement, velocity, and acceleration. The gyro sensor 22 detects the physical movement of the terminal device 10, such as its tilt in the three axes, based on its angular velocity. The barometric pressure sensor 23 detects the atmospheric pressure around the terminal device 10, for example.

[0064] Since the terminal device 10 is equipped with the acceleration sensor 21, gyroscope 22, barometric pressure sensor 23, etc., it becomes possible to determine the position of the terminal device 10 using technologies such as pedestrian dead-reckoning (PDR) that utilize these sensors 21 to 23. This makes it possible to obtain indoor location information that is difficult to obtain with positioning systems such as GPS.

[0065] For example, a pedometer using an accelerometer 21 can calculate the number of steps, walking speed, and distance walked. Additionally, a gyroscope 22 can be used to determine the user U's direction of movement, gaze direction, and body tilt. Furthermore, the barometric pressure detected by the barometric pressure sensor 23 can be used to determine the altitude and floor number of the user U's terminal device 10.

[0066] The temperature sensor 24 detects, for example, the ambient temperature around the terminal device 10. The sound sensor 25 detects, for example, the ambient sound around the terminal device 10. The light sensor 26 detects the ambient illumination around the terminal device 10. The magnetic sensor 27 detects, for example, the Earth's magnetic field around the terminal device 10. The image sensor 28 captures an image of the area around the terminal device 10.

[0067] The aforementioned pressure sensor 23, temperature sensor 24, sound sensor 25, light sensor 26, and image sensor 28 can detect the surrounding environment and conditions of the terminal device 10 by detecting atmospheric pressure, temperature, sound, and illuminance, respectively, and by capturing images of the surroundings. Furthermore, it becomes possible to improve the accuracy of the location information of the terminal device 10 based on the surrounding environment and conditions.

[0068] (Control Unit 30) The control unit 30 includes, for example, a microcomputer having a CPU (Central Processing Unit), ROM (Read Only Memory), RAM, input / output ports, and various circuits. Alternatively, the control unit 30 may be composed of hardware such as an integrated circuit (ASIC) or FPGA (Field Programmable Gate Array). The control unit 30 includes a transmission unit 31, a reception unit 32, and a processing unit 33.

[0069] (Transmitter 31) The transmission unit 31 can transmit various information, such as information input by the user U using the input unit 13, various information detected by sensors 21-28 mounted on or connected to the terminal device 10, and location information of the terminal device 10 determined by the positioning unit 14, to the server device 100 via the communication unit 11.

[0070] (Receiving unit 32) The receiving unit 32 can receive various information provided by the server device 100, as well as requests for various information from the server device 100, via the communication unit 11.

[0071] (Processing 33) The processing unit 33 controls the entire terminal device 10, including the display unit 12. For example, the processing unit 33 can output and display various information transmitted by the transmission unit 31 and various information received from the server device 100 by the reception unit 32 to the display unit 12.

[0072] (Storage unit 40) The storage unit 40 is implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or by storage devices such as HDD (Hard Disk Drive), SSD (Solid State Drive), and optical discs. Various programs and various data are stored in this storage unit 40.

[0073] [4. Example of Server Device Configuration] Next, the configuration of the server device 100 according to the embodiment will be described using Figure 6. Figure 6 is a diagram showing an example of the configuration of the server device 100 according to the embodiment. As shown in Figure 6, the server device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

[0074] (Communications Department 110) The communication unit 110 is implemented, for example, by a NIC (Network Interface Card). The communication unit 110 is connected to the network N (see Figure 4) by wire or wireless connection.

[0075] (Storage unit 120) The storage unit 120 is implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or by storage devices such as HDDs, SSDs, and optical discs. As shown in Figure 6, the storage unit 120 has a user information database 121, a history information database 122, and an unambiguous information database 123.

[0076] (User Information Database 121) The user information database 121 stores user information about user U. For example, the user information database 121 stores various information such as user U's attributes. Figure 7 shows an example of the user information database 121. In the example shown in Figure 7, the user information database 121 has items such as "User ID (Identifier)", "Age", "Gender", "Home", "Workplace", and "Interests".

[0077] "User ID" refers to identification information used to identify user U. Note that "User ID" may be user U's contact information (telephone number, email address, etc.) or identification information used to identify user U's terminal device 10.

[0078] Furthermore, "Age" indicates the age of user U, identified by the user ID. Note that "Age" may be information indicating user U's specific age (e.g., 35 years old), or information indicating user U's age group (e.g., 30s), or "Age" may be information indicating user U's date of birth, or information indicating user U's generation (e.g., born in the 1980s). Furthermore, "Gender" indicates the gender of user U, identified by the user ID.

[0079] Furthermore, "Home" indicates the location information of user U's home, which is identified by the user ID. In the example shown in Figure 7, "Home" is represented by an abstract code such as "LC11," but it could also be latitude and longitude information, etc. Also, for example, "Home" could be a regional name or address.

[0080] Furthermore, "Workplace" indicates the location information of the workplace (or school in the case of a student) of user U, identified by the user ID. In the example shown in Figure 7, "Workplace" is illustrated with an abstract code such as "LC12," but it may also be latitude and longitude information, etc. Also, for example, "Workplace" may be a regional name or address.

[0081] Furthermore, "Interests" indicate the interests of user U, who is identified by their user ID. In other words, "Interests" indicate the subjects of high interest to user U, who is identified by their user ID. For example, "Interests" may be search queries (keywords) that user U enters into a search engine. In the example shown in Figure 7, one "Interest" is shown for each user U, but there may be multiple interests.

[0082] For example, in the example shown in Figure 7, user U, identified by user ID "U1", is in their 20s and is male. Also, for example, user U, identified by user ID "U1", has their home address at "LC11". Furthermore, for example, user U, identified by user ID "U1", has their workplace at "LC12". Finally, for example, user U, identified by user ID "U1", is interested in "sports".

[0083] In the example shown in Figure 7, abstract values ​​such as "U1," "LC11," and "LC12" are used to illustrate the information, but it is assumed that "U1," "LC11," and "LC12" actually store specific strings, numbers, or other information. In the following diagrams relating to other information, abstract values ​​may also be used to illustrate the information.

[0084] The user information database 121 is not limited to the above and may store various types of information depending on the purpose. For example, the user information database 121 may store various types of information about user U's terminal device 10. In addition, the user information database 121 may store information about user U's demographic, psychographic, geographic, and behavioral attributes. For example, the user information database 121 may store information such as name, family structure, place of origin (hometown), occupation, job title, income, qualifications, type of residence (detached house, apartment, etc.), whether or not a car is owned, commuting time, commuting route, commuter pass section (station, line, etc.), frequently used stations (other than the nearest station to home / workplace), lessons / classes (location, time, etc.), hobbies, interests, and lifestyle.

[0085] (History Information Database 122) The history information database 122 stores various information related to the history information (log data) that shows the user U's actions. Figure 8 shows an example of the history information database 122. In the example shown in Figure 8, the history information database 122 has items such as "User ID", "Location History", "Search History", "Browsing History", "Purchase History", and "Posting History".

[0086] "User ID" indicates identification information used to identify user U. "Location History" indicates the location history, which is the history of user U's location and movements. "Search History" indicates the search history, which is the history of search queries entered by user U. "Browsing History" indicates the browsing history, which is the history of content viewed by user U. "Purchase History" indicates the purchase history, which is the history of purchases made by user U. "Posting History" indicates the posting history, which is the history of posts made by user U. Note that "Posting History" may include questions about user U's possessions.

[0087] For example, in the example shown in Figure 8, user U, identified by user ID "U1", moves as described in "Location History #1", searches as described in "Search History #1", views content as described in "Browsing History #1", purchases specified goods at specified stores as described in "Purchase History #1", and posts as described in "Posting History #1".

[0088] In the example shown in Figure 8, abstract values ​​such as "U1", "Location History #1", "Search History #1", "Browsing History #1", "Purchase History #1", and "Posting History #1" are used for illustration. However, it is assumed that "U1", "Location History #1", "Search History #1", "Browsing History #1", "Purchase History #1", and "Posting History #1" will actually store specific strings, numbers, and other information.

[0089] The history information database 122 is not limited to the above and may store various types of information depending on the purpose. For example, the history information database 122 may store the usage history of user U for a specified service. The history information database 122 may also store the visit history of user U to a physical store or a facility. The history information database 122 may also store the payment history of user U using the terminal device 10 for payments (electronic payments).

[0090] (Non-ambiguous information database 123) The non-ambiguous information database 123 stores various information related to the user U's actions (log data). Figure 9 shows an example of the non-ambiguous information database 123. In the example shown in Figure 9, the non-ambiguous information database 123 has items such as "proper nouns," "non-ambiguous," and "co-occurring words."

[0091] A "proper noun" refers to a proper noun (keyword, etc.) that indicates a specific object (such as a location name). This includes both unambiguous proper nouns (unambiguous domain-specific words), which are used uniquely to indicate a specific object, and ambiguous proper nouns (ambiguous domain-specific words), which can be used not only to indicate a specific object but also for other purposes.

[0092] Furthermore, "unambiguous" indicates whether a proper noun is unambiguous or not. For example, it indicates whether a proper noun is an unambiguous proper noun or an ambiguous proper noun.

[0093] Furthermore, "co-occurring words" refer to strings of characters (co-occurring words, etc.) that have a relationship with a proper noun. For example, co-occurring words include search queries entered with unambiguous proper nouns (unambiguous co-occurring word queries) and search queries entered with ambiguous proper nouns (ambiguous co-occurring word queries).

[0094] For example, in the example shown in Figure 9, the proper noun "Kioi Tower" is a non-ambiguous proper noun ("Yes") and also has a relationship (co-occurs) with co-occurring words such as "directions, access, restaurant."

[0095] Furthermore, the non-ambiguous information database 123 is not limited to the above and may store various types of information depending on the purpose. For example, the non-ambiguous information database 123 may store information about the attributes or segments of user U who searched for proper nouns together with co-occurring words. In addition, the non-ambiguous information database 123 may store information about a model (binary classifier) ​​that performs binary classification of whether or not a proper noun is non-ambiguous, or information about a dictionary of non-ambiguous proper nouns.

[0096] (Control unit 130) Returning to Figure 6, let's continue the explanation. The control unit 130 is a controller, and is realized by various programs (corresponding to an example of an information processing program) stored in the internal memory of the server device 100, such as a CPU (Central Processing Unit), MPU (Micro Processing Unit), ASIC (Application Specific Integrated Circuit), or FPGA (Field Programmable Gate Array), executing them using a memory area such as RAM as the working area. In the example shown in Figure 6, the control unit 130 has an acquisition unit 131, a learning unit 132, a detection unit 133, a dictionary generation unit 134, and an application unit 135.

[0097] (Acquisition part 131) The acquisition unit 131 acquires search queries entered by user U. For example, when user U enters a search query into a search engine or the like and performs a keyword search, the acquisition unit 131 acquires the search query via the communication unit 110. In other words, the acquisition unit 131 acquires keywords entered by user U into the search box of a search engine, website, or application via the communication unit 110.

[0098] Furthermore, the acquisition unit 131 acquires user information about user U via the communication unit 110. For example, the acquisition unit 131 acquires identification information (such as user ID), location information, and attribute information of user U from user U's terminal device 10. The acquisition unit 131 may also acquire identification information and attribute information of user U when user U is registered. The acquisition unit 131 then registers the user information in the user information database 121 of the storage unit 120.

[0099] Furthermore, the acquisition unit 131 acquires various historical information (log data) indicating the user U's actions via the communication unit 110. For example, the acquisition unit 131 acquires various historical information indicating the user U's actions from the user U's terminal device 10, or from various servers based on the user ID, etc. The acquisition unit 131 then registers the various historical information in the history information database 122 of the storage unit 120.

[0100] In this embodiment, the acquisition unit 131 acquires proper nouns (keywords, etc.) and strings associated with those proper nouns (co-occurring words, etc.) via the communication unit 110. The proper nouns may be extracted from readily available entity name lists (publicly available web pages, databases, etc.). The associated strings may be, for example, search queries entered together with the proper nouns, or words that frequently appear together with the proper nouns in papers or content. Furthermore, the proper nouns and associated strings may be strings that appear in text documents. Additionally, the proper nouns and strings may be strings extracted from image data by image recognition, or strings extracted from audio data by speech recognition.

[0101] For example, the acquisition unit 131 acquires non-ambiguous proper nouns (non-ambiguous domain-specific words) that are used uniquely with the intention of indicating a specific object (such as a base name), and strings that are associated with non-ambiguous proper nouns. In this case, the acquisition unit 131 may acquire non-ambiguous proper nouns that are used uniquely with the intention of indicating a specific object, ambiguous proper nouns (ambiguous domain-specific words) that can be used not only with the intention of indicating a specific object but also with other intentions, and strings that are associated with non-ambiguous proper nouns or ambiguous proper nouns.

[0102] (Learning Section 132) The learning unit 132 uses non-ambiguous proper nouns that are used uniquely to indicate a specific object, and strings associated with non-ambiguous proper nouns, to build a model that estimates whether an input proper noun is a non-ambiguous proper noun through learning.

[0103] For example, the learning unit 132 uses unambiguous proper nouns that are uniquely used to indicate a specific object, ambiguous proper nouns that can be used not only to indicate a specific object but also for other purposes, and strings associated with unambiguous or ambiguous proper nouns to build a model that estimates whether an input proper noun is an unambiguous or ambiguous proper noun through learning.

[0104] Furthermore, the learning unit 132 uses pairs of unambiguous proper nouns and strings associated with them, and pairs of ambiguous proper nouns and strings associated with them, as training datasets to construct a model (binary classifier) ​​that classifies input proper nouns as either unambiguous or ambiguous.

[0105] Furthermore, the learning unit 132 constructs a classifier that classifies input proper nouns related to location names (landmarks, etc.) into either unambiguous or ambiguous landmark words, using unambiguous landmark words that are uniquely used to indicate location names (landmarks, etc.) as unambiguous proper nouns, ambiguous landmark words that can be used not only to indicate location names as ambiguous proper nouns but also for other purposes, and co-occurring words of either unambiguous or ambiguous landmark words, as described above.

[0106] Furthermore, the learning unit 132 uses unambiguous proper nouns, ambiguous proper nouns, and search queries input along with unambiguous or ambiguous proper nouns to construct a classifier that classifies input proper nouns into either unambiguous or ambiguous proper nouns, as described above.

[0107] Furthermore, the learning unit 132 uses search query text for pre-training (in contrast to the usual use of general text). For example, the learning unit 132 performs unsupervised learning without labels using search query text as pre-training. For instance, similar to the pre-training method of BERT which uses a pre-trained model, the learning unit 132 randomly hides (masks) tokens (≒words) in the text and has the model infer the hidden (masked) parts.

[0108] Furthermore, during this training, the learning unit 132 learns by inputting pairs of proper nouns and search queries (co-occurring words) as input data (in contrast to the usual practice of using only proper nouns as input data). For example, as part of this training, the learning unit 132 inputs pairs of proper nouns and co-occurring words (pairs of unambiguous proper nouns and co-occurring words, or pairs of ambiguous proper nouns and co-occurring words) into the model and learns to classify them into either unambiguous or ambiguous proper nouns.

[0109] Furthermore, the learning unit 132 performs unsupervised learning without using labels during pre-training, and performs supervised learning using non-ambiguous or ambiguous labels during the main training.

[0110] (Detection unit 133) The detection unit 133 inputs proper nouns into a trained model and detects (automatically extracts) unambiguous proper nouns. Alternatively, the detection unit 133 may input strings related to proper nouns along with the proper nouns into the trained model and detect unambiguous proper nouns.

[0111] (Dictionary generation unit 134) The dictionary generation unit 134 automatically generates a dictionary of unambiguous proper nouns based on the detected unambiguous proper nouns.

[0112] (Applicable part 135) The application unit 135 incorporates or adds the above-mentioned model or non-ambiguous proper noun dictionary to the existing system, thereby applying the above-mentioned model or non-ambiguous proper noun dictionary to the existing system without modifying the existing system, and enabling the detection of non-ambiguous proper nouns in the existing system. Alternatively, the application unit 135 may be a providing unit that provides the above-mentioned model or non-ambiguous proper noun dictionary to an external party via the communication unit 110.

[0113] [5. Processing Procedure] Next, the processing procedure by the server device 100 according to the embodiment will be described using Figure 10. Figure 10 is a flowchart of the processing procedure according to the embodiment. Note that the processing procedure shown below is repeatedly executed by the control unit 130 of the server device 100.

[0114] For example, as shown in Figure 10, the acquisition unit 131 of the server device 100 acquires proper nouns and co-occurring words that co-occur with those proper nouns via the communication unit 110 (step S101). In this embodiment, the acquisition unit 131 acquires non-ambiguous proper nouns that are uniquely used with the intention of indicating a specific object, ambiguous proper nouns that can be used not only with the intention of indicating a specific object but also with other intentions, and co-occurring words that co-occur with non-ambiguous or ambiguous proper nouns.

[0115] Next, the learning unit 132 of the server device 100 performs unsupervised learning without labels using the search query text as pre-training, in which it randomly hides (masks) tokens (≒words) in the text and has the model infer the hidden parts (masked parts) (step S102).

[0116] Next, the learning unit 132 of the server device 100, as part of the main learning process, inputs pairs of proper nouns and co-occurring words (pairs of unambiguous proper nouns and co-occurring words, or pairs of ambiguous proper nouns and co-occurring words) into the model (binary classifier) ​​and learns to classify them into either unambiguous or ambiguous proper nouns (step S103).

[0117] Next, the detection unit 133 of the server device 100 inputs proper nouns into a trained model (binary classifier) ​​to detect (automatically extract) unambiguous proper nouns (step S104). At this time, the detection unit 133 may also input co-occurring words along with the proper nouns into the trained model to detect unambiguous proper nouns.

[0118] Next, the dictionary generation unit 134 of the server device 100 automatically generates a dictionary of unambiguous proper nouns based on the detected unambiguous proper nouns (step S105).

[0119] Next, the application unit 135 of the server device 100 incorporates or adds the above-mentioned model (binary classifier) ​​or non-ambiguous proper noun dictionary to the existing system, thereby applying the above-mentioned model or non-ambiguous proper noun dictionary to the existing system without modifying the existing system, and enabling the detection of non-ambiguous proper nouns in the existing system (step S106).

[0120] [6. Variant Example] The terminal device 10 and server device 100 described above may be implemented in various other forms besides those of the embodiment described above. Therefore, the following describes modifications of the embodiment.

[0121] In the above embodiment, some or all of the processing performed by the server device 100 may actually be performed by the terminal device 10. For example, the processing may be completed in a standalone manner (by the terminal device 10 alone). In this case, the terminal device 10 is assumed to have the functions of the server device 100 in the above embodiment. Furthermore, in the above embodiment, since the terminal device 10 is in cooperation with the server device 100, from the perspective of the user U, it appears as if the processing of the server device 100 is also being performed by the terminal device 10. In other words, from another perspective, it can be said that the terminal device 10 is equipped with the server device 100.

[0122] Furthermore, in the above embodiment, the server device 100 may, after inputting proper nouns into the model (binary classifier), output a score indicating the degree of confidence that a proper noun is unambiguous, rather than simply whether or not it is an unambiguous proper noun, as output of the model (binary classifier). The server device 100 may then automatically construct (automatically generate) an unambiguous proper noun dictionary (unambiguous domain-specific word dictionary) based on proper nouns (unambiguous proper nouns) whose scores are above a threshold. The score may be, for example, the output of a softmax function. The threshold may be a predetermined value or may be arbitrarily set.

[0123] Furthermore, in the above embodiment, the server device 100 may construct separately a model that classifies whether a proper noun is a non-ambiguous proper noun or not when a proper noun is input, and a model that classifies whether a proper noun is an ambiguous proper noun or not when a proper noun is input. In other words, the model for detecting non-ambiguous proper nouns and the model for detecting ambiguous proper nouns may be independent of each other.

[0124] Furthermore, in the above embodiment, the server device 100 may, as a method for explicitly adding co-occurring words to proper nouns during the main learning process (transfer learning / fine tuning), sample 3 million web search queries, divide each web search query by space delimiters, and construct a co-occurring word dictionary for each word. In this case, up to 10 different co-occurring words are randomly collected for each target word. Next, the obtained co-occurring words are linked to the target noun, which is the input to the model, with [SEP] tokens to generate input data with co-occurring words (e.g., "Kioi Tower [SEP] access [SEP] directions [SEP] restaurant"). The [SEP] token is a token that represents a sentence separator [SEP]. By linking with [SEP] tokens in this way, BERT can distinguish between the target noun that is actually to be classified and the co-occurring words that are additional information. Note that the target word and co-occurring words may be linked simply by space delimiters instead of [SEP] tokens.

[0125] Furthermore, it has been empirically observed that non-ambiguous domain-specific words (non-ambiguous landmark words) appear less frequently in web search queries compared to common nouns and words with meanings other than landmarks. Therefore, in the above embodiment, a rule may be created to define nouns that appear below a certain frequency (below a threshold) in web search queries as non-ambiguous landmark words. As the threshold, the value that yields the highest F1 score in the training data may be used.

[0126] Furthermore, many words that can become non-ambiguous domain-specific words (non-ambiguous landmark words) have specific suffixes, such as "○○ Hospital" and "○○ Post Office." Therefore, in the above embodiment, a suffix dictionary of words that can become non-ambiguous domain-specific words (non-ambiguous landmark words) may be constructed in advance, and a rule may be created to designate a word as a non-ambiguous landmark word if its suffix matches that dictionary. The suffix dictionary may be a collection of frequently occurring suffixes from words included in a manually created non-ambiguous landmark word dictionary.

[0127] [7. Effects] As described above, the information processing device (terminal device 10 and server device 100) according to the present invention comprises: a learning unit 132 that builds a model by learning to estimate whether an input proper noun is a non-ambiguous proper noun, using non-ambiguous proper nouns that are used uniquely with the intention of indicating a specific object and strings associated with the non-ambiguous proper nouns; a detection unit 133 that inputs proper nouns into the trained model and detects non-ambiguous proper nouns; and a dictionary generation unit 134 that automatically generates a non-ambiguous proper noun dictionary based on the detected non-ambiguous proper nouns.

[0128] The learning unit 132 constructs a model that estimates whether an input proper noun is an unambiguous or ambiguous proper noun by learning from unambiguous proper nouns that are used uniquely with the intention of referring to a specific object, ambiguous proper nouns that can be used not only with the intention of referring to a specific object but also with other intentions, and strings that are associated with unambiguous or ambiguous proper nouns.

[0129] The learning unit 132 uses pairs of unambiguous proper nouns and strings associated with them, and pairs of ambiguous proper nouns and strings associated with them, as training datasets to build a model that classifies input proper nouns as either unambiguous or ambiguous.

[0130] The learning unit 132 constructs a classifier that classifies input proper nouns related to location names into either unambiguous or ambiguous landmark words, using unambiguous landmark words that are used uniquely with the intention of indicating location names as unambiguous proper nouns, ambiguous landmark words that can be used not only with the intention of indicating location names as ambiguous proper nouns but also with other intentions, and co-occurring words of either unambiguous or ambiguous landmark words, as described above.

[0131] The learning unit 132 uses unambiguous proper nouns, ambiguous proper nouns, and search queries input along with either unambiguous or ambiguous proper nouns to construct a classifier that classifies input proper nouns into either unambiguous or ambiguous proper nouns, as described above.

[0132] The learning unit 132 performs unsupervised learning using search query text as pre-training, randomly masking tokens in the text and having the model infer the masked parts.

[0133] The learning unit 132, as part of its main learning process, inputs pairs of proper nouns and co-occurring words into the model and learns to classify them into either unambiguous proper nouns or ambiguous proper nouns.

[0134] The learning unit 132 performs unsupervised learning without using labels during pre-training, and performs supervised learning using non-ambiguous or ambiguous labels during main training.

[0135] The detection unit 133 inputs a proper noun along with a string associated with the proper noun into a trained model to detect unambiguous proper nouns.

[0136] Furthermore, the information processing device according to the present invention further includes an application unit 135 that enables the detection of unambiguous proper nouns in an existing system by incorporating or adding the above-mentioned model or unambiguous proper noun dictionary to the existing system without modifying the existing system.

[0137] By any or a combination of the above-described processes, the information processing device according to the present invention can automatically construct a dictionary of non-ambiguous domain-specific terms.

[0138] [8. Hardware Configuration] Furthermore, the terminal device 10 and server device 100 according to the above-described embodiment are realized by a computer 1000 having a configuration such as that shown in Figure 11. The following explanation will use the server device 100 as an example. Figure 11 is a diagram showing an example of the hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 1030, a primary storage device 1040, a secondary storage device 1050, an output interface 1060, an input interface 1070, and a network interface 1080 are connected by a bus 1090.

[0139] The arithmetic unit 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, as well as programs read from the input device 1020, and executes various processes. The arithmetic unit 1030 can be implemented using, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), an ASIC (Application Specific Integrated Circuit), or an FPGA (Field Programmable Gate Array).

[0140] The primary storage device 1040 is a memory device, such as RAM (Random Access Memory), that temporarily stores data used by the arithmetic unit 1030 for various calculations. The secondary storage device 1050 is a storage device where data used by the arithmetic unit 1030 for various calculations and various databases are registered, and can be implemented using ROM (Read Only Memory), HDD (Hard Disk Drive), SSD (Solid State Drive), flash memory, etc. The secondary storage device 1050 may be internal storage or external storage. The secondary storage device 1050 may also be a removable storage medium such as USB (Universal Serial Bus) memory or SD (Secure Digital) memory card. The secondary storage device 1050 may also be cloud storage (online storage), NAS (Network Attached Storage), file server, etc.

[0141] The output I / F 1060 is an interface for transmitting information to be output to output devices 1010, such as displays, projectors, and printers, and is implemented using connectors of standards such as USB (Universal Serial Bus), DVI (Digital Visual Interface), and HDMI (High Definition Multimedia Interface). The input I / F 1070 is an interface for receiving information from various input devices 1020, such as mice, keyboards, keypads, buttons, and scanners, and is implemented using, for example, USB.

[0142] Furthermore, the output interface 1060 and input interface 1070 may be wirelessly connected to the output device 1010 and input device 1020, respectively. In other words, the output device 1010 and input device 1020 may be wireless devices.

[0143] Furthermore, the output device 1010 and the input device 1020 may be integrated as a touch panel. In this case, the output I / F 1060 and the input I / F 1070 may also be integrated as an input / output I / F.

[0144] The input device 1020 may also be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), DVD (Digital Versatile Disc), or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0145] The network interface 1080 receives data from other devices via network N and sends it to the computing unit 1030, and also transmits data generated by the computing unit 1030 to other devices via network N.

[0146] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output interface 1060 and the input interface 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0147] For example, when computer 1000 functions as a server device 100, the arithmetic unit 1030 of computer 1000 realizes the functions of the control unit 130 by executing a program loaded onto the primary storage device 1040. Alternatively, the arithmetic unit 1030 of computer 1000 may load a program obtained from another device via the network interface 1080 onto the primary storage device 1040 and execute the loaded program. Furthermore, the arithmetic unit 1030 of computer 1000 may cooperate with other devices via the network interface 1080 and call and use program functions, data, etc., from other programs on other devices.

[0148] [9. Other] Although embodiments of the present invention have been described above, the present invention is not limited by the content of these embodiments. Furthermore, the aforementioned components include those that can be easily conceived by those skilled in the art, those that are substantially the same, and those that fall within the so-called equivalent range. Moreover, the aforementioned components can be combined as appropriate. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the gist of the embodiments described above.

[0149] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0150] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0151] For example, the server device 100 described above may be implemented using multiple server computers, and the configuration can be flexibly changed, such as by calling external platforms via APIs (Application Programming Interfaces) or network computing depending on the function.

[0152] Furthermore, the embodiments and modifications described above can be combined as appropriate, provided that the processing content is not inconsistent.

[0153] Furthermore, the terms "section, module, unit" mentioned above can be replaced with "means" or "circuit," etc. For example, the acquisition unit can be replaced with acquisition means or acquisition circuit. [Explanation of Symbols]

[0154] 1. Information Processing System 10 Terminal devices 100 Server Devices 110 Communications Department 120 Storage section 121 User Information Database 122 History Information Database 123 Non-ambiguous information database 130 Control Unit 131 Acquisition Department 132 Learning Department 133 Detection unit 134 Dictionary Generation Unit 135 Application section

Claims

1. A learning unit constructs a model that, through learning, estimates whether an input proper noun is a non-ambiguous proper noun based on the input proper noun and the string associated with the input proper noun, using a non-ambiguous proper noun that is used uniquely with the intention of referring to a specific object and a string associated with the non-ambiguous proper noun. A detection unit that uses the trained model to detect unambiguous proper nouns based on the input proper noun and a string associated with that proper noun, A dictionary generation unit that automatically generates a dictionary of non-ambiguous proper nouns based on the detected non-ambiguous proper nouns. Equipped with, The string associated with the aforementioned proper noun is the string entered together with the proper noun in the search. An information processing device characterized by the following:

2. The learning unit constructs a model that uses, through learning, the non-ambiguous proper nouns that are used uniquely with the intention of indicating a specific object, strings associated with the non-ambiguous proper nouns, ambiguous proper nouns that can be used not only with the intention of indicating a specific object but also with other intentions, and strings associated with the ambiguous proper nouns, to estimate whether the input proper noun is a non-ambiguous proper noun or an ambiguous proper noun based on the input proper noun and the strings associated with the proper noun. The information processing apparatus according to feature 1.

3. The learning unit uses the pairs of non-ambiguous proper nouns and strings associated with them, and the pairs of ambiguous proper nouns and strings associated with them, as training datasets to build a model that classifies input proper nouns as either non-ambiguous or ambiguous proper nouns based on the input proper nouns and the strings associated with them. The information processing apparatus according to feature 2.

4. The learning unit uses the non-ambiguous landmark words, which are used uniquely with the intention of indicating a location name as a non-ambiguous proper noun, the co-occurring words of the non-ambiguous landmark words as strings associated with the non-ambiguous proper noun, the ambiguous landmark words, which can be used not only with the intention of indicating a location name as an ambiguous proper noun but also with other intentions, and the co-occurring words of the ambiguous landmark words as strings associated with the ambiguous proper noun, to construct a classifier as a model that classifies the input proper nouns relating to location names into non-ambiguous landmark words or ambiguous landmark words based on the input proper nouns relating to location names and the co-occurring words of said proper nouns. The information processing apparatus according to feature 2.

5. The learning unit uses the non-ambiguous proper noun, the search query input together with the non-ambiguous proper noun as a string related to the non-ambiguous proper noun, and the ambiguous proper noun, and the search query input together with the ambiguous proper noun as a string related to the ambiguous proper noun, to construct a classifier as a model that classifies the input proper noun as either a non-ambiguous proper noun or an ambiguous proper noun based on the input proper noun and the search query input together with the proper noun. The information processing apparatus according to feature 2.

6. The aforementioned learning unit performs unsupervised learning using search query text as pre-training, in which tokens in the text are randomly masked and the model is made to infer the masked portion. The information processing apparatus according to feature 2.

7. The learning unit, as part of its learning process, inputs pairs of proper nouns and co-occurring words into the model and learns to classify them into either unambiguous proper nouns or ambiguous proper nouns. The information processing apparatus according to feature 2.

8. The aforementioned learning unit performs unsupervised learning without using labels during pre-training, and supervised learning using non-ambiguous or ambiguous labels during the main training. The information processing apparatus according to feature 2.

9. The detection unit inputs a proper noun along with a string associated with the proper noun into the trained model to detect unambiguous proper nouns. The information processing apparatus according to claim 1 or 2.

10. An application unit that enables the detection of unambiguous proper nouns in an existing system by incorporating or adding the model or the unambiguous proper noun dictionary to an existing system without modifying the existing system. The information processing apparatus according to claim 1 or 2, further comprising:

11. An information processing method performed by an information processing device, A learning process that constructs a model that estimates whether an input proper noun is a non-ambiguous proper noun based on the input proper noun and the string associated with the input proper noun, using a non-ambiguous proper noun that is used uniquely with the intention of referring to a specific object and a string associated with the non-ambiguous proper noun. A detection step that uses the trained model to detect unambiguous proper nouns based on the input proper noun and the string associated with that proper noun, A dictionary generation process that automatically generates a dictionary of unambiguous proper nouns based on the detected unambiguous proper nouns. Includes, The string associated with the aforementioned proper noun is the string entered together with the proper noun in the search. An information processing method characterized by the following:

12. A learning procedure for constructing a model that uses non-ambiguous proper nouns, which are used uniquely to indicate a specific object, and strings associated with the said non-ambiguous proper nouns, to estimate whether an input proper noun is a non-ambiguous proper noun based on the input proper noun and the strings associated with the said proper noun. A detection procedure for detecting unambiguous proper nouns based on an input proper noun and a string associated with that proper noun, using the trained model described above. A dictionary generation procedure that automatically generates a dictionary of unambiguous proper nouns based on detected unambiguous proper nouns. An information processing program that causes a computer to execute, The string associated with the aforementioned proper noun is the string entered together with the proper noun in the search. An information processing program characterized by the following features.

Images