Retrieval device, retrieval method, and retrieval program

Abstract

To provide a retrieval device, retrieval method, and retrieval program, which enable more accurately retrieving a location from a retrieval query entered by a user.SOLUTION: In a retrieval device 100, a control unit 130 comprises: an acquisition unit 131 for acquiring a retrieval query entered by a user and a latitude and longitude indicative of a current location of the user; a conversion unit 132 for converting the latitude and longitude into an address; a coupling unit 133 for coupling the retrieval query and the address into one character string; and a retrieval unit 134 configured to input the character string to a machine learning model to retrieve a location and output the retrieved location, the machine learning model designed to output location information corresponding to a retrieval query.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present invention relates to a search device, a search method, and a search program. [Background technology]

[0002] A user can access a search site or application using a smartphone or the like to search for information on various locations such as landmarks, convenience stores, hotels, etc. In such a location search, for example, a user inputs a search query such as the name of a location into an input form of a search site or the like via a smartphone or the like, and the location is searched for using a DNN (Deep Neural Network) based on the search query.

[0003] In addition, in a location search, the location indicated by the search query entered by the user may change depending on the user's current location. Therefore, for example, location information may be obtained from a smartphone or the like used by the user, and a search may be performed for a location more desired by the user using the search query and the location information. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2007-233863 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the location information that can be obtained from a smartphone, etc., is latitude and longitude information indicating the current location obtained using the GPS (Global Positioning System) function of the smartphone, etc. In addition, the DNN used in the base search is good at interpreting natural language, but is not good at interpreting numerical strings such as latitude and longitude, so it is difficult to correctly search for bases using latitude and longitude information (at least, to perform a correct search, a very large-scale machine learning model and training data are required, which is not easy).

[0006] The present application has been made in consideration of the above, and has an object to more accurately search for locations from a search query input by a user. [Means for solving the problem]

[0007] The search device according to the present application is characterized by having an acquisition unit that acquires a search query input by a user and latitude and longitude indicating the user's current location, a conversion unit that converts the latitude and longitude into an address, a combination unit that connects the search query and the address into a single character string, and a search unit that inputs the character string into a machine learning model that outputs information about locations from the search query, and searches for and outputs the locations. Effect of the Invention

[0008] According to one aspect of the present embodiment, it is possible to more accurately search for locations based on a search query input by a user. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing an example of a problem in a location search. [Diagram 2] FIG. 2 is a diagram showing an example of the configuration of the information processing system 1 according to the present embodiment. [Diagram 3] FIG. 3 is a diagram showing an example of a base search according to the present embodiment. [Figure 4]FIG. 4 is a diagram showing an example of the configuration of a search device 100 according to this embodiment. [Diagram 5] FIG. 5 is a diagram showing an example of information stored in the input data storage unit 121 according to the present embodiment. [Figure 6] FIG. 6 is a diagram showing an example of training data according to the present embodiment. [Figure 7] FIG. 7 is a flowchart showing an example of a procedure of the base search process according to the present embodiment. [Figure 8] FIG. 8 is a flowchart showing an example of a procedure of the training process according to this embodiment. [Figure 9] FIG. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the search device 100. As shown in FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, a detailed description will be given of a search device, a search method, and a search program according to the present application (hereinafter, referred to as an "embodiment") with reference to the drawings. Note that the search device, the search method, and the search program according to the present application are not limited to the embodiment. In addition, the same components in the following embodiments are given the same reference numerals, and duplicated descriptions are omitted.

[0011] [0. Problem] First, an example of a base search will be described with reference to FIG. 1. When searching for a base such as a convenience store, a user accesses a search site using a smartphone or the like and inputs a search query into an input form, which returns information on bases that are hit by the search. FIG. 1 is a diagram showing an example of a problem with base searches. However, for example, as shown in FIG. 1, when the search query is only the name of the base, the user's current location may be required to search for and hit the base that the user wants to know about. For example, as shown in FIG. 1, if the search query is "XXX Mart", a user currently at Shinjuku Station is likely to want to know about the nearest "XXX Mart Shinjuku Station West Exit Store", and a user currently at Kokusai-dori Shopping Street is likely to want to know about the nearest "XXX Mart Naha Kokusai-dori Store". For example, if a user currently at Shinjuku Station wants to obtain information on "XXX Mart Naha Kokusai-dori Store", the user would enter "XXX Mart Naha Kokusai-dori Store" as a search query. Therefore, it is believed that a more accurate location search can be performed by performing a search that takes into account not only the search query but also the user's current location.

[0012] However, since the location information of the current location that can be obtained from a smartphone or the like is a numerical string indicating latitude and longitude, in this embodiment, the numerical string is converted into a character string (address) that is more suitable for the DNN used in the base search, so that the search can be performed in natural language. Also, since there are cases where the user's current location does not need to be taken into consideration, such as when the search query is "Tokyo Tower" (it is clear that the "Tokyo Tower" pointed to by the search query is the only Tokyo Tower no matter where the user is), in this embodiment, a machine learning model is trained so that the DNN can determine for itself whether or not to use the current location when searching for bases.

[0013] [1. Configuration of information processing system] With reference to FIG. 2, information processing realized by the search device 100 and the like of this embodiment will be described. FIG. 2 is a diagram showing a configuration example of an information processing system 1 according to this embodiment. In the example shown in FIG. 2, the information processing system 1 has a user terminal 10 and a search device 100. The user terminal 10 and the search device 100 are connected to each other so as to be able to communicate with each other by wire or wirelessly via a predetermined communication network not shown. The network N is a communication network such as a LAN (Local Area Network), a WAN (Wide Area Network), a telephone network (such as a mobile phone network or a landline telephone network), a regional IP (Internet Protocol) network, or the Internet. The network N may include a wired network or a wireless network. The information processing system 1 shown in FIG. 2 may include a plurality of user terminals 10 and a plurality of search devices 100.

[0014] The user terminal 10 shown in Fig. 2 is an information processing terminal used by a user who performs a base search. For example, the user terminal 10 is a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), etc. In the example shown in Fig. 2, the user terminal 10 is a smart device such as a smartphone or tablet used by a user.

[0015] The user terminal 10 shown in FIG. 2 displays, for example, a search site or application for searching locations provided by the search device 100 or the like, and transmits a search query that a user inputs into an input form of the search site or the like to search for locations to the search device 100. Note that input into the input form for the search query may be, for example, not only text input but also voice input. The user terminal 10 also transmits, for example, latitude and longitude information indicating a current location acquired using a GPS function, together with the search query to the search device 100. The user terminal 10 also receives and displays, for example, a search result for locations from the search device 100.

[0016] 2 is an information processing device managed by a service provider that provides a base search service. For example, the search device 100 is a server computer. Alternatively, the search device 100 may be a cloud computer device managed by a service provider that provides a cloud computing service.

[0017] The search device 100 shown in FIG. 2 receives and acquires, for example, a search query input by a user and latitude and longitude indicating the user's current location from the user terminal 10. The search device 100 also converts, for example, the acquired latitude and longitude into an address. The search device 100 also combines, for example, the acquired search query and the converted address into one character string. The search device 100 then inputs, for example, the combined character string into a machine learning model that outputs information on bases from the search query, searches for bases, and outputs the search results to the user terminal 10. The base search of this embodiment will be described in more detail with reference to FIG. 3.

[0018] FIG. 3 is a diagram showing an example of a base search according to the present embodiment. As shown in FIG. 3, the search device 100 uses, for example, a query DNN, which is a machine learning model that outputs a query vector, which is vector data of a base, from a search query, and a base DNN, which is a machine learning model that outputs a base vector, which is vector data of a base, from base information, to perform a vector search using the vector data of the base output from the query DNN and the base DNN, and searches for a base. Note that data input to the query DNN is, for example, a character string combining a search query and an address input by a user. Also, data input to the base DNN is, for example, a name, address, telephone number, etc. of a base.

[0019] 2. Configuration of the Search Device Next, the configuration of the search device 100 will be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of the configuration of the search device 100 according to this embodiment. As shown in Fig. 4, the search device 100 has a communication unit 110, a storage unit 120, and a control unit 130.

[0020] (Regarding communication unit 110) The communication unit 110 is realized by, for example, a network interface card (NIC) etc. The communication unit 110 is connected to a network N by wire or wirelessly, and transmits and receives information to and from other devices such as the user terminal 10.

[0021] (Regarding the storage unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 4, the storage unit 120 has an input data storage unit 121, an address data storage unit 122, and a model data storage unit 123.

[0022] (Regarding the input data storage unit 121) The input data storage unit 121 stores, for example, data to be input to a machine learning model for base search. An example of input data stored in the input data storage unit 121 will now be described with reference to FIG. 5. FIG. 5 is a diagram showing an example of information stored in the input data storage unit 121 according to this embodiment. In the example of FIG. 5, the input data storage unit 121 stores data items such as "search query," "current location / latitude and longitude," "current location / address," and "input value" in association with each other.

[0023] The "search query" is, for example, a search query input by a user via the user terminal 10. The "current location / latitude and longitude" is, for example, latitude and longitude indicating the current location acquired using the GPS function of the user terminal 10. The "current location / address" is, for example, an address obtained by converting latitude and longitude information indicating the current location. The "input value" is, for example, an input value (character string) input to a machine learning model for base search. For example, as shown in FIG. 5, the "input value" may be a character string in which the search query and the address indicating the current location are connected with a predetermined prefix. This allows the machine learning model for base search to be trained to distinguish, for example, the search query input by the user, which is included in the input value, from the added current location, and to determine for itself whether or not to use the current location when searching for bases.

[0024] (Regarding the address data storage unit 122) The address data storage unit 122 stores, for example, data for converting latitude and longitude indicating the current location acquired using the GPS function of the user terminal 10 into an address. The information stored in the address data storage unit 122 is, for example, data in which latitude and longitude are associated with an address or a specified area.

[0025] (Regarding the model data storage unit 123) The model data storage unit 123 stores, for example, information about a machine learning model for outputting information about a location from a search query, and model parameters for constructing the machine learning model. The machine learning model is generated by training, for example, using a character string in which a search query and an address are combined as input data, and a vector indicating a location as a correct answer label. Note that the machine learning model is, for example, the query DNN shown in FIG. 3, and corresponds to the first machine learning model.

[0026] Furthermore, when training the machine learning model in the search device 100, the model data storage unit 123 may store, for example, training data for the machine learning model. FIG. 6 is a diagram showing an example of training data according to this embodiment. In the example of FIG. 6, the training data is stored in association with data items such as "input data" and "correct label / location". The "input data" is, for example, a character string formed by combining a search query and an address with a predetermined prefix, which may be input to the machine learning model for location search. The "correct label / location" is, for example, vector data of a location that is a correct answer for the "input data".

[0027] Furthermore, the model data storage unit 123 stores, for example, information on a machine learning model for outputting vector data of bases from base information, and model parameters for constructing the machine learning model. The machine learning model is generated, for example, by training using base information as input data and vectors indicating bases as answer labels. Note that the machine learning model is, for example, the base DNN shown in FIG. 3, and corresponds to the second machine learning model. Furthermore, when training the machine learning model in the search device 100, for example, training data for the machine learning model may be stored in the model data storage unit 123.

[0028] (Regarding the control unit 130) The control unit 130 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the search device 100 using a RAM as a working area. The control unit 130 is also a controller, and is realized, for example, by an integrated circuit such as an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a GPGPU (General Purpose Graphic Processing Unit). As shown in FIG. 4, the control unit 130 according to this embodiment has an acquisition unit 131, a conversion unit 132, a combination unit 133, a search unit 134, and a training unit 135, and realizes or executes the functions and actions of information processing described below.

[0029] (Regarding the acquisition unit 131) The acquisition unit 131 receives and acquires, for example, a search query input by the user via the user terminal 10, and latitude and longitude indicating the user's current location acquired using the GPS function of the user terminal 10 from the user terminal 10. The search query and latitude and longitude acquired from the user terminal 10 may be stored in the input data storage unit 121. In addition, the acquisition unit 131 acquires user attributes including, for example, at least one of the user's gender, age, and generation. The user attributes may be input by the user via the user terminal 10 together with the search query and stored in the input data storage unit 121 or the like, or may be stored in advance as user information in the storage unit 120 or the like.

[0030] (Regarding the conversion unit 132) The conversion unit 132 converts, for example, the latitude and longitude acquired by the acquisition unit 131 into an address. Note that the conversion into the address may use, for example, data stored in the address data storage unit 122.

[0031] (Regarding the joint 133) The combining unit 133 combines, for example, the search query acquired by the acquiring unit 131 and the address converted by the converting unit 132 into one character string. The process of combining the character strings may include, for example, a process of combining the search query and the address with a predetermined prefix into one character string. The process of combining the character strings may also include, for example, a process of combining the search query, the address, and the user attribute acquired by the acquiring unit 131 with a predetermined prefix into one character string.

[0032] (Regarding the search unit 134) The search unit 134, for example, inputs the character string combined by the combination unit 133 to a machine learning model that outputs information about locations from a search query, and searches for and outputs the locations. Note that the process of searching for and outputting locations may include a process of performing a vector search using the vector data of locations output from both machine learning models, using a machine learning model that outputs vector data of locations from a search query and a machine learning model that outputs vector data of locations from location information, as shown in Fig. 3, and searching for and outputting the locations. More specifically, the process of searching for and outputting the base may include, for example, a process of inputting the character string combined by the combining unit 133 into a first machine learning model generated by training using a first character string combined with the first search query and the first address as first input data and a first vector indicating the first base as a first correct answer label to obtain a third vector output, and performing a vector search using a fourth vector output from a second machine learning model generated by training using information on a second base associated with a second search query of a URL displayed in the base search result by the search unit 134 as second input data and a second vector indicating the second base as a second correct answer label, and the third vector. Note that, for example, the first machine learning model is the query DNN shown in FIG. 3, and the second machine learning model is the base DNN shown in FIG. 3. Furthermore, the character string input to the machine learning model may include, for example, a search query, an address, and user attributes including the user's gender, age, and generation, and the location search may be further based on the user attributes. For example, the machine learning model may be trained by further including the user attributes in the training data so that locations more suitable for the user's gender and age are searched.

[0033] (Regarding Training Division 135) The training unit 135 trains and generates a first machine learning model using, for example, the first input data and the first correct answer label. For example, the first machine learning model is a query DNN shown in FIG. 3, the first input data is a first character string in which the first search query and the first address are combined, and the first correct answer label is a first vector indicating the first location. In addition, the first input data and the first correct answer label are generated based on a click log of a URL (Uniform Resource Locator) displayed in the search result of the location by the search unit 134 in order to train the first machine learning model to determine whether or not to use the first address included in the first input data. For example, since a URL clicked from the search result of the location by the search unit 134 is considered to be a URL related to the location that is a correct answer to the location search, the training unit 135 can use vector data of the location corresponding to the URL as the correct answer label of the training data, and the character string input to the machine learning model at that time as the input data of the training data. Training a machine learning model to determine whether or not to use an address contained in input data means, for example, when searching for Tokyo Tower, no matter what the current location address is added, if the clicked URL points to Tokyo Tower, then by generating training data based on the clicked URL, the machine learning model can be trained to know that the current location address does not need to be used in searching for Tokyo Tower locations (for example, the model can be trained to have less influence from the address).

[0034] The training unit 135 also trains and generates a second machine learning model using, for example, the second input data and the second correct label. For example, the second machine learning model is the location DNN shown in FIG. 3, the second input data is information on the second location, and the second correct label is a second vector indicating the second location linked to a second search query of a URL displayed in the search result for the location by the search unit 134. The second input data and the second correct label may also be generated based on a click log of a URL displayed in the search result for the location by the search unit 134, for example, in order to train the second machine learning model to determine whether to use the address of the location.

[0035] Note that, when training of the machine learning model is performed, for example, in an information processing device other than the search device 100, the search device 100 does not need to include the training unit 135.

[0036] [3. Location search processing flow] The procedure of the base search process of the information processing system 1 according to this embodiment will be described with reference to Fig. 7. Fig. 7 is a flowchart showing an example of the procedure of the base search process according to this embodiment.

[0037] As shown in FIG. 7, the search device 100 acquires, for example, a search query input by a user via the user terminal 10, and latitude and longitude indicating the user's current location acquired using the GPS function of the user terminal 10 from the user terminal 10 (step S101).

[0038] Next, the search device 100 converts, for example, the latitude and longitude acquired in step S101 into an address (step S102).

[0039] Next, the search device 100 combines, for example, the search query acquired in step S101 and the address converted in step S102 into one character string (step S103).

[0040] Next, the search device 100 inputs, for example, the character string combined in step S103 into a machine learning model that outputs information about locations from the search query, and searches for locations (step S104).

[0041] Next, the search device 100 outputs, for example, the search result of the location searched in step S104 (step S105). Note that the output of the search result may be, for example, by transmitting the search result to the user terminal 10 and displaying it via a display device. After executing step S105, the location search process shown in FIG. 7 ends.

[0042] [4. Training process flow] The procedure of the training process by the search device 100 according to this embodiment will be described with reference to Fig. 8. Fig. 8 is a flowchart showing an example of the procedure of the training process according to this embodiment.

[0043] 8, the search device 100 acquires from the user terminal 10 a click log of a URL displayed in a search result of a location output to the user terminal 10 by, for example, the location search process shown in FIG. 7 (step S201). The click log may be collected from each of the user terminals 10 by the search device 100 and stored in the storage unit 120, for example.

[0044] Next, the search device 100 generates input data and a correct answer label for training a machine learning model that outputs information about locations from the search query, for example, based on the click log acquired in step S201 (step S202). For example, based on the click log, vector data of the location corresponding to the clicked URL from the search results for the locations is used as the correct answer label, and the character string input to the machine learning model at that time is used as input data.

[0045] Next, the search device 100 trains and generates a machine learning model that outputs information about locations from a search query using, for example, the input data and the correct answer label generated in step S202 (step S203). After step S203 is executed, the training process shown in FIG. 8 ends.

[0046] 5. Effects As described above, the search device 100 according to this embodiment includes an acquisition unit 131 that acquires a search query input by a user and latitude and longitude indicating the user's current location, a conversion unit 132 that converts the latitude and longitude into an address, a combination unit 133 that connects the search query and the address into one character string, and a search unit 134 that inputs the character string into a machine learning model that outputs information about bases from the search query, and searches for and outputs the bases.

[0047] This allows the search device 100 according to this embodiment to more accurately search for locations based on a search query input by a user.

[0048] Furthermore, the process of combining character strings executed by the search device 100 according to this embodiment includes a process of combining the search query and the address into one character string by connecting them with a predetermined prefix.

[0049] This allows the search device 100 according to the present embodiment to distinguish between the search query input by the user and the added address.

[0050] In addition, the process of searching for and outputting locations executed by the search device 100 according to this embodiment includes a process of inputting a character string into a first machine learning model generated by training using a first character string formed by combining a first search query and a first address as first input data and a first vector indicating the first location as a first correct answer label to obtain a third vector output, and performing a vector search using a fourth vector output from a second machine learning model generated by training using information about the second location as second input data and a second vector indicating the second location linked to the second search query of a URL displayed in the search results for locations by the search unit 134 as a second correct answer label, and the third vector.

[0051] This allows the search device 100 according to this embodiment to more accurately search for locations based on a search query input by a user.

[0052] In addition, the first input data and the first correct answer label used by the search device 100 of this embodiment are generated based on the click log of the URL displayed in the search result of the location by the search unit 134 in order to train the first machine learning model to determine whether or not to use the first address included in the first input data.

[0053] This allows the search device 100 according to this embodiment to train the machine learning model so that it can determine by itself whether or not to use the current location when searching for bases.

[0054] Moreover, the search device 100 according to this embodiment includes a training unit 135 that trains and generates a first machine learning model using the first input data and the first correct answer label.

[0055] This allows the search device 100 according to this embodiment to more accurately search for locations based on a search query input by a user.

[0056] In addition, the second input data and the second correct answer label used by the search device 100 in this embodiment are generated based on the click log of the URL displayed in the search result for the base by the search unit 134 in order to train the second machine learning model to determine whether or not to use the address of the base.

[0057] This allows the search device 100 according to this embodiment to train the machine learning model so that it can determine by itself whether or not to use the address of a base when searching for a base.

[0058] Moreover, the search device 100 according to this embodiment includes a training unit 135 that trains and generates a second machine learning model using the second input data and the second correct answer label.

[0059] This allows the search device 100 according to this embodiment to more accurately search for locations based on a search query input by a user.

[0060] In addition, the search device 100 according to this embodiment has an acquisition unit 131 that acquires user attributes including at least one of the user's gender, age, and generation, and the process of combining strings executed by the search device 100 includes a process of combining the search query, address, and user attributes into one string by connecting them with a predetermined prefix.

[0061] In this way, the search device 100 according to this embodiment can search for locations more suitable for the user based on the search query input by the user.

[0062] [6. Hardware Configuration] Moreover, the information processing devices according to the above-described embodiments are realized, for example, by a computer 1000 configured as shown in Fig. 9. The following description will be given taking the search device 100 as an example. Fig. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the search device 100. The computer 1000 has a CPU 1100, a ROM 1200, a RAM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0063] The CPU 1100 operates and controls each unit based on a program stored in the ROM 1200 or the HDD 1400. The ROM 1200 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, programs that depend on the hardware of the computer 1000, and the like.

[0064] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a communication network 500 (corresponding to the network N in this embodiment) and sends the data to the CPU 1100, and also transmits data generated by the CPU 1100 to other devices via the communication network 500.

[0065] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs data generated via the input / output interface 1600 to the output devices.

[0066] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1300. CPU 1100 loads the program from recording medium 1800 onto RAM 1300 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0067] For example, when the computer 1000 functions as the search device 100, the CPU 1100 of the computer 1000 executes a program loaded onto the RAM 1300 to realize the function of the control unit 130. In addition, the HDD 1400 stores each piece of data in the storage device of the search device 100. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from another device via a predetermined communication network.

[0068] [7. Other] Although some of the present embodiments have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be embodied in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the Disclosure of the Invention section.

[0069] Furthermore, the above-described search device 100 can be flexibly modified in configuration, for example, by calling an external platform or the like using an API (Application Programming Interface) or network computing to implement some functions.

[0070] Furthermore, the term "unit" in the claims may be read as "means" or "circuit," etc. For example, an acquisition unit may be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0071] 10 User terminal 100 Search device 110 Communications Department 120 Storage section 121 Input data storage unit 122 Address data storage unit 123 Model Data Storage Unit 130 Control section 131 Acquisition Department 132 Conversion unit 133 Joint 134 Search Department 135 Training Department

Claims

1. An acquisition unit that acquires a search query input by a user and a latitude and longitude indicating a current location of the user; A conversion unit that converts the latitude and longitude into an address; a combining unit that combines the search query and the address into one character string; a search unit that inputs the character string into a machine learning model that outputs information about locations based on the search query, searches for the locations, and outputs the information; A search device comprising:

2. The process of joining the character strings includes: The search query and the address are joined with a predetermined prefix to form a single character string.

2. The search device according to claim 1, further comprising a process for:

3. The process of searching for and outputting the bases includes: inputting the character string into a first machine learning model generated by training using a first character string obtained by combining a first search query and a first address as first input data and a first vector indicating a first base location as a first correct answer label, and acquiring a third vector that is output; A vector search is performed using the third vector and a fourth vector output from a second machine learning model generated by training information about a second location using second input data and a second vector indicating the second location, the second vector being associated with a second search query of a uniform resource locator (URL) displayed in a search result for the location by the search unit, as a second correct answer label, and the third vector, to output the location.

2. The search device according to claim 1, further comprising a process for:

4. The search device according to claim 3, characterized in that the first input data and the first correct answer label are generated based on a click log of a URL displayed in a search result for the location by the search unit, in order to train the first machine learning model to determine whether or not to use the first address included in the first input data.

5. The search device according to claim 3 or 4, further comprising a training unit that trains and generates the first machine learning model using the first input data and the first correct label.

6. The search device described in claim 3, characterized in that the second input data and the second correct answer label are generated based on a click log of a URL displayed in a search result for the location by the search unit in order to train the second machine learning model to determine whether or not to use the address of the location.

7. The search device according to claim 3 or 6, further comprising a training unit that trains and generates the second machine learning model using the second input data and the second correct label.

8. The acquisition unit is Acquire user attributes including at least one of the user's gender, age, and generation; The process of joining the character strings includes: The search query, the address, and the user attribute are joined with a predetermined prefix to form a single character string.

2. The search device according to claim 1, further comprising a process for:

9. A search method executed by a search device, comprising: acquiring a search query entered by a user and a latitude and longitude indicating a current location of the user; a conversion step of converting the latitude and longitude into an address; a combining step of combining the search query and the address into one character string; a search step of inputting the character string into a machine learning model that outputs information on locations based on the search query, and searching for and outputting the locations; A search method comprising:

10. an acquisition step for acquiring a search query entered by a user and a latitude and longitude indicating a current location of the user; a conversion step of converting the latitude and longitude into an address; a combining step of combining the search query and the address into a single string; a search step of inputting the character string into a machine learning model that outputs information on locations based on the search query, and searching for and outputting the locations; A search program that causes a computer to execute the following.

Images