Information processing apparatus, information processing method, and information processing program

Abstract

To output a name of a commodity in an appropriate style.SOLUTION: An information processing apparatus includes: an extraction unit which extracts a name term to be used for a name of a commodity, from among terms, based on similarities between the terms associated with the commodity corresponding to a search query input by a user in a predetermined e-commerce service; a generation unit which generates a name of the commodity, based on the name terms extracted by the extraction unit; and an output unit which outputs the name generated by the generation unit to the user via the predetermined e-commerce service.SELECTED DRAWING: Figure 3

Description

[Technical Field]

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

[0002] Conventionally, there are known techniques for providing search results in response to a search query entered by a user. One example of such a technique is a technique for extracting products from a group of products that fit within a range specified by the search query, and providing the search results. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2023-113238 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned techniques may not be able to output the product name in an appropriate manner.

[0005] For example, the above-mentioned conventional technology merely outputs content showing products within a range specified by a search query, and cannot be said to be able to output product names in an appropriate manner.

[0006] The present application has been made in view of the above, and aims to output the name of a product in an appropriate manner. [Means for solving the problem]

[0007] The information processing device of the present application is characterized by having an extraction unit that extracts name terms to be used in the name of a product from terms linked to a product corresponding to a search query entered by a user in a specified e-commerce service based on the similarity between the terms, a generation unit that generates a name of the product based on the name terms extracted by the extraction unit, and an output unit that outputs the name generated by the generation unit to the user via the specified e-commerce service. [Effects of the Invention]

[0008] According to one aspect of the embodiment, it is possible to produce an effect that the name of the product can be output in an appropriate manner. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Figure 2] FIG. 2 is a diagram showing an example of a screen of the user terminal 100 according to the embodiment. [Figure 3] FIG. 3 is a diagram showing an example of the configuration of the information processing device 10 according to the embodiment. [Figure 4] FIG. 4 is a diagram showing an example of the product information database 31. As shown in FIG. [Figure 5] FIG. 5 is a diagram showing an example of the user information database 32. As shown in FIG. [Figure 6] FIG. 6 is a flowchart illustrating an example of a procedure for information processing according to the embodiment. [Figure 7] FIG. 7 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 10. As shown in FIG. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, an information processing device, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the same components in the following embodiments will be denoted by the same reference numerals, and duplicated descriptions will be omitted.

[0011] 1. Embodiment Information processing implemented by an information processing device or the like according to this embodiment will be described using Fig. 1. Fig. 1 is a diagram showing an example of information processing according to this embodiment. Note that in Fig. 1, it is assumed that information processing according to this embodiment is implemented by an information processing device 10, which is an example of an information processing device according to this embodiment.

[0012] As shown in Fig. 1, an information processing system 1 according to the embodiment includes an information processing device 10 and a user terminal 100. The information processing device 10 and the user terminal 100 are connected to each other via a network N (see Fig. 3, for example) so as to be able to communicate with each other via a wired or wireless connection. The network N is, for example, a wide area network (WAN) such as the Internet. Note that the information processing system 1 shown in Fig. 1 may include a plurality of information processing devices 10 and a plurality of user terminals 100.

[0013] 1 is an information processing device that performs information processing, and is realized by, for example, a server device, a cloud system, or the like. For example, the information processing device 10 receives input of product information from a product provider, including information such as terms associated with the product (e.g., a noun indicating the product, a character string indicating the product category, a character string indicating the product features, etc.), an image indicating the product (product image), and a description of the product, and manages the input in a storage unit of the information processing device 10. Then, the information processing device 10 provides an e-commerce service #1 to a user based on the product information.

[0014] In addition, e-commerce service #1 may be, for example, an electronic mall with multiple stores, an e-commerce site operated by an administrator of an information processing device, or a flea market service or auction service where products put up for sale by a user (provider) are purchased by other users.

[0015] The information processing device 10 may also have a function as a web server that provides websites related to various services including services related to the e-commerce service #1. The information processing device 10 may also be a device that distributes information to the user terminal 100 to be displayed in applications related to various services installed in the user terminal 100. The information processing device 10 may also be a server that distributes the application data itself.

[0016] Furthermore, the information processing device 10 may function as a distribution device that distributes control information to the user terminal 100. Here, the control information is written in, for example, a script language such as JavaScript (registered trademark) or a style sheet language such as CSS (Cascading Style Sheets). Note that the application itself distributed from the information processing device 10 may be regarded as the control information.

[0017] The user terminal 100 shown in Fig. 1 is an information processing device used by a user. The user terminal 100 is realized, for example, by a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. The user terminal 100 displays information distributed by the information processing device 10 or the like using a web browser or an application. In the example shown in Fig. 1, the user terminal 100 is a smartphone.

[0018] An example of information processing performed by the information processing device 10 will be described below with reference to FIG. 1. In the following description, it is assumed that the user terminal 100 is used by a user (user U1) identified by a user ID "UID#1." In the following description, the user terminal 100 may be considered to be the same as the user U1. In other words, in the following description, the user U1 may also be read as the user terminal 100.

[0019] First, the information processing device 10 receives a search query entered by user U1 in e-commerce service #1 from the user terminal 100 (step S1). In the example of FIG. 1, it is assumed that user U1 has entered the search query "electric heater." In this case, the information processing device 10 refers to its own storage unit, identifies products #1, #2, #3, ... that correspond to the search query "electric heater," and extracts product information corresponding to the identified products.

[0020] Next, the information processing device 10 extracts similar terms based on the similarity between the terms linked to the identified products (step S2). For example, the information processing device 10 converts each term linked to the product into a vector using model #1 that converts character strings into vectors. Then, the information processing device 10 clusters each term mapped onto the vector space based on the similarity of the vectors, and extracts each term belonging to the same cluster as mutually similar terms (in other words, terms whose mutual similarity is equal to or greater than a predetermined threshold).

[0021] For example, in the example of FIG. 1 , it is assumed that product #1 is linked to term group #1 (the terms “electric heater,” “electric stove,” “energy saving,” “electricity bill,” “heater,” “for 12-tatami rooms,” “fan heater,” “fast heating,” “instant heating,” “stylish,” and “with casters”). In this case, the information processing device 10 classifies the terms “electric heater,” “electric stove,” “heater,” and “fan heater” into the same cluster (similar term group #1). The information processing device 10 also classifies the terms “energy saving” and “electricity bill” into the same cluster (similar term group #2). The information processing device 10 also classifies the terms “fast heating” and “instant heating” into the same cluster (similar term group #3). Note that the information processing device 10 does not classify the term “for 12-tatami rooms” into a cluster because there are no other similar terms in term group #1. Similarly, the information processing device 10 does not classify "stylish" and "wheeled" into clusters.

[0022] Note that the training of the above model #1 may be performed using, for example, various techniques related to word2vec.

[0023] Furthermore, the information processing device 10 may set the similarity between terms (vectors) based on the Euclidean distance in the vector space. For example, the information processing device 10 sets the similarity between terms to be higher as the Euclidean distance between the vectors corresponding to the terms in the vector space becomes shorter.

[0024] Furthermore, the information processing device 10 may extract similar terms using a model that has been trained to generate answers to input questions. For example, the information processing device 10 extracts similar terms by inputting a question regarding whether multiple terms are similar. For example, the information processing device 10 inputs a question such as "Do 'electric heater' and 'electric stove' have the same meaning? Please answer yes or no" into the model, and if the model outputs "yes," the information processing device 10 extracts the terms "electric heater" and "electric stove" as terms that are similar to each other.

[0025] Such a model is a model trained to output an answer corresponding to an input question, and is a language model that performs natural language processing, such as GPT (Generative Pre-trained Transformer) or BERT (Bidirectional Encoder Representations from Transformers). Such a model is stored within the information processing device 10 and is independently created by the business entity that manages the information processing device 10. It is desirable to keep input information, such as personal information, confidential by training the model so that the input information is not used as a new answer.

[0026] Next, the information processing device 10 extracts name terms to be used in the name of the product from the terms linked to the product (step S3). For example, the information processing device 10 extracts terms that are not classified into any cluster (in other words, terms that have no other similar terms) from the term group #1, such as "for a 12-tatami room," "stylish," and "with casters," as name terms to be used in the name of product #1. Furthermore, the information processing device 10 extracts the most important term from each cluster of the similar term groups #1 to #3 as the name term to be used in the name of product #1.

[0027] To give a specific example, the information processing device 10 assigns a higher importance to a term that matches more closely with the search query "electric heater" entered by user U1. Furthermore, the information processing device 10 assigns a higher importance to a term that matches more closely with the description of product #1 (in other words, a more reliable term). Then, the information processing device 10 extracts the term with the highest importance from each cluster of similar term groups #1 to #3 as a name term.

[0028] In the example of FIG. 1, the term "electric heater" is extracted from similar term group #1, the term "energy saving" is extracted from similar term group #2, and the term "quick heating" is extracted from similar term group #3 as name terms.

[0029] Next, the information processing device 10 generates a product name based on the name terms (step S4). For example, the information processing device 10 generates a product name based on the name term group #1 of product #1. To give a specific example, the information processing device 10 arranges the name terms #1 in the order entered by the provider of product #1, and generates the product name as the product #1.

[0030] 1, the provider of product #1 inputs term group #1 in the following order: "electric heater," "electric stove," "energy saving," "electricity bill," "heater," "for 12-tatami mat room," "fan heater," "fast heating," "instant heating," "stylish," and "with casters." In this case, the information processing device 10 arranges the name terms #1 in the order entered by the provider, and generates the name of product #1 as "electric heater, energy saving, for 12-tatami mat room, fast heating, stylish, with casters."

[0031] Next, the information processing device 10 outputs the generated product name to the user terminal 100 via the e-commerce service #1 (step S5). For example, the information processing device 10 generates names of other products #2, #3, ... that correspond to the search query "electric heater" using a method similar to that described above. Then, the information processing device 10 outputs search results that indicate the generated names of products #1, #2, #3, ...

[0032] An example of a screen showing search results provided to the user terminal 100 will now be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of a screen of the user terminal 100 according to the embodiment.

[0033] For example, when the search results are displayed without performing the processing of steps S2 and S3 described above, a name is generated by arranging the terms associated with the product in the order entered by the product provider, as shown on screen C1, and is displayed on the user terminal 100. To give a specific example, the user terminal 100 displays a name in the display area AR1 for the name of product #1, in which term group #1 is arranged in the order entered by the provider of product #1. Here, if there is a character limit in the display area AR1 (for example, 20 characters or less), multiple similar character strings (in other words, character strings with overlapping meanings) such as "electric heater," "electric stove," and "heater" are displayed, and character strings indicating the characteristics of product #1, such as "for 12 tatami mats," "quick heating," and "stylish," are hidden.

[0034] In contrast, when the above-mentioned processing of steps S2 and S3 is performed and the search results are displayed, a name is generated in which similar character strings are deleted from the terms linked to the product, as shown on screen C2, and is displayed on the user terminal 100. To give a specific example, in the display area AR2 of the name of product #1, the user terminal 100 deletes character strings such as "electric stove" and "heater" that are similar to "electric heater," and instead displays character strings that indicate the characteristics of product #1, such as "for 12 tatami mats," "quick heating," and "stylish."

[0035] As described above, the information processing device 10 according to the embodiment extracts similar terms from among terms linked to products, and generates and outputs the name of the product based on the most important term among the extracted terms. This allows the information processing device 10 according to the embodiment to output the name of the product in an appropriate manner.

[0036] In addition, in the past, providers sometimes associated multiple similar terms with a product, such as "electric heater," "electric stove," "heater," and "fan heater," with the aim of matching the product to various search queries. In such cases, as shown in Figure 2, if a product name is generated by arranging the terms in the order entered by the provider, faithfulness to the information entered (set) by the provider regarding the product is ensured, but the generated name may be redundant for users. Furthermore, if such names are displayed as a list of search results, users may not be able to grasp the characteristics of each product.

[0037] Therefore, the information processing device 10 of the embodiment extracts the most important terms from among similar terms and generates the name of the product, thereby ensuring fidelity to the information entered by the provider and eliminating redundant expressions, allowing the user to understand the characteristics of each listed product.

[0038] [2. Other processing examples] The above-described process is merely an example, and the information processing device 10 may perform various processes using various information. In this regard, examples are listed below.

[0039] [2-1. Extracting name terms from a group of similar terms] 1, the information processing device 10 may extract a name term from a group of similar terms without using the importance of each term. For example, the information processing device 10 may extract the term that was input earliest by the provider from the group of similar terms.

[0040] [2-2. Importance] 1, the information processing device 10 may set the importance of a term using any method. For example, the information processing device 10 may set the importance using model #2 that has been trained to output the importance when a term is input.

[0041] Note that when a learning term is input, the above model #2 is trained to output a level of importance according to the user's reaction to the term. For example, if a user is presented with first content about a product whose name includes a first learning term and second content about a product whose name includes a second learning term, and the first content has a higher CTR (Click Through Rate) than the second content, model #2 is trained to output a higher score when the first term is input into model #2 than when the second term is input.

[0042] In this way, any known technology can be applied to the training of model #2, and a learning method appropriately selected depending on the information used as training data may be used. For example, the training of model #2 may be performed using various conventional machine learning technologies (e.g., supervised machine learning technologies such as SVM (Support Vector Machine)). Furthermore, the training of model #2 may be performed using deep learning technologies. For example, the training of model #2 may be performed using various deep learning technologies such as RNN (Recurrent Neural Network) and CNN (Convolutional Neural Network).

[0043] [2-3. Extracting name terms based on search queries] In the example of FIG. 1, if user U1 inputs the search query "electric heater," user U1 knows that search results will display products that refer to "electric heater," so the importance of the term "electric heater" may be low. For this reason, the information processing device 10 may assign a lower importance to terms that match the search query "electric heater" input by user U1 more closely. The information processing device 10 may then extract terms other than "electric heater" from the similar term group #1 as name terms.

[0044] Furthermore, since user U1 knows that products similar to "electric heater" will be output, the importance of "electric stove," "heater," and "fan heater," which are similar to the term "electric heater," may be low. For this reason, the information processing device 10 may generate the name of product #1 without using the term "electric heater" or terms belonging to similar term group #1.

[0045] [2-4. Extraction of name terms based on product images] In the example of FIG. 1, the information processing device 10 may set a higher importance for a term that matches product image #1 showing product #1. For example, the information processing device 10 may set a higher importance for a term that matches the character string "sokudan" (fast warming) detected from product image #1 using any image recognition technology. As a specific example, the information processing device 10 extracts the term "sokudan" (fast warming), which matches the character string detected from product image #1, from similar term group #3 as a name term.

[0046] Note that, since the character string "sokudan" (quick warming) is included in the product image #1, the importance of the term "sokudan" and the term "instant warming" (instant warming) similar to "sokudan" may be low. For this reason, the information processing device 10 may generate the name of the product #1 without using the term "sokudan" or the terms belonging to the similar term group #3.

[0047] [2-5. Extraction of name terms based on term distinctiveness] 1, the information processing device 10 may set an importance indicating the distinctiveness of a term for product #1. For example, the information processing device 10 sets a higher importance for a term when the number of products linked to the term is smaller, and extracts the name term.

[0048] [2-6. Generating patterns of term combinations] 1, the information processing device 10 may generate a plurality of patterns of combinations of term group #1. Then, the information processing device 10 may calculate a score for each pattern based on the importance of each included term and the similarity between each included term, and extract a pattern whose score satisfies a predetermined condition as a name term. As a specific example, the information processing device 10 extracts, as a name term, the pattern with the highest value obtained by subtracting the similarity between each included term from the sum of the importance of each included term.

[0049] [2-7. Name Generation] In the example of FIG. 1, the information processing device 10 may generate a name by arranging the name term group #1 in descending order of importance.

[0050] Furthermore, the information processing device 10 may generate a name from the name term group #1 so that the number of characters in the name is equal to or less than the character limit of the display area shown in Fig. 2. For example, the information processing device 10 generates the name of product #1 by deleting name terms so that the number of characters in the name is equal to or less than the character limit of the display area shown in Fig. 2. To give a specific example, the information processing device 10 removes name terms with lower importance from the name term group #1 and generates the name of product #1 so that the number of characters is equal to or less than the character limit.

[0051] [2-8. Processing according to the number of characters] In the example of Fig. 1, the information processing device 10 may not perform the process of extracting name terms if the total number of characters of the terms linked to the product is equal to or less than the character limit of the display area shown in Fig. 2. In such a case, the information processing device 10 may generate a product name by arranging the terms linked to the product in the order entered by the product provider, and output the generated product name to the user terminal 100. The information processing device 10 may also generate a product name by arranging the terms linked to the product in the order of importance, and output the generated product name to the user terminal 100.

[0052] [2-9. Name generation using models] In the example of Figure 1, the information processing device 10 may generate the name of product #1 by inputting a group of terms #1 to model #3, which has been trained to output the name of the product (for example, a name set by an administrator of e-commerce service #1) when a term linked to the product is input.

[0053] 1, the information processing device 10 may generate the name of product #1 using term group #1 and model #4 that has been trained to generate an answer to an input question. For example, the information processing device 10 generates the name of product #1 by inputting term group #1 and an instruction sentence that instructs model #4 to output the name of product #1 (in other words, a summary of term group #1) based on term group #1. Here, the information processing device 10 outputs, as the name of product #1, a name generated by model #4 that does not include terms other than term group #1, and does not output, as the name of product #1, a name that includes terms other than term group #1.

[0054] Model #4 is a model trained to output an answer corresponding to an input question, and is a language model that performs natural language processing such as GPT (Generative Pre-trained Transformer) or BERT (Bidirectional Encoder Representations from Transformers). Model #4 is stored in information processing device 10 and was independently created by the business operator that manages information processing device 10. It is desirable to train the input information so that it will not be used as a new answer, thereby keeping the input information, such as personal information, confidential.

[0055] 3. Configuration of Information Processing Device Next, the configuration of the information processing device 10 will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the configuration of the information processing device 10 according to an embodiment. As shown in Fig. 3, the information processing device 10 has a communication unit 20, a storage unit 30, and a control unit 40.

[0056] (Regarding the communication unit 20) The communication unit 20 is realized by, for example, a network interface card (NIC), etc. The communication unit 20 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the user terminal 100, etc.

[0057] (Regarding the storage unit 30) The storage unit 30 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. 3 , the storage unit 30 has a product information database 31, a user information database 32, and a model database 33.

[0058] (About Product Information Database 31) The product information database 31 stores various information related to products provided via e-commerce services. An example of the information stored in the product information database 31 will now be described with reference to FIG. 4. FIG. 4 is a diagram showing an example of the product information database 31. In the example of FIG. 4, the product information database 31 has items such as "product ID," "category," "term information," "product image," and "description."

[0059] "Product ID" indicates identification information for identifying a product. "Category" indicates the category to which the product belongs. "Term information" indicates information about the terms linked to the product, and stores information such as character strings indicating the terms and the order in which each term was entered by the provider. "Product image" indicates an image of the product. "Description" indicates a description of the product.

[0060] That is, Figure 4 shows an example in which the category to which the product identified by the product ID "CID#1" belongs is "Category #1", the term associated with the product is "Term Information #1", the product image of the product is "Product Image #1", and the description of the product is "Description #1".

[0061] (Regarding User Information Database 32) The user information database 32 stores various types of information related to users. An example of the information stored in the user information database 32 will now be described with reference to Fig. 5. Fig. 5 is a diagram showing an example of the user information database 32. In the example of Fig. 5, the user information database 32 has items such as "user ID," "attribute information," "search history," and "browsing history."

[0062] "User ID" indicates identification information for identifying a user. "Attribute information" indicates information related to the user's attributes, such as information indicating demographic attributes and psychographic attributes. "Search history" indicates the user's search history (e.g., search queries) in e-commerce services and various other services. "Browsing history" indicates the user's browsing history in e-commerce services and various other services.

[0063] That is, FIG. 5 shows an example in which the attribute information of a user identified by a user ID "UID#1" is "attribute information #1", the search history is "search history #1", and the browsing history is "browsing history #1".

[0064] (About Model Database 33) The model database 33 stores a model that converts a character string into a vector. The model database 33 also stores a model that has been trained to output an importance level when a term is input. The model database 33 also stores a model that has been trained to output the name of a product when a term linked to the product is input. The model database 33 also stores a model that has been trained to generate an answer to an input question.

[0065] (Regarding the control unit 40) The control unit 40 is a controller, and is realized by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the information processing device 10 using RAM as a work area. The control unit 40 is also a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). As shown in FIG. 3 , the control unit 40 according to the embodiment has an extraction unit 41, a generation unit 42, and an output unit 43, and realizes or executes the functions and actions of information processing described below.

[0066] (Regarding the extraction unit 41) The extraction unit 41 extracts name terms to be used for product names from the terms based on the similarity between terms linked to products corresponding to a search query entered by a user in a predetermined e-commerce service. For example, in the example of Fig. 1, the extraction unit 41 refers to the product information database 31 and the model database 33, vectorizes character strings, and extracts name terms based on the similarity of the vectors.

[0067] The extraction unit 41 may further extract name terms based on the importance and similarity of each term. For example, in the example of Fig. 1, the extraction unit 41 extracts name term group #1 based on the importance of each term in term group #1 and the similarity between the terms.

[0068] The extraction unit 41 may also extract name terms based on the importance indicating the degree of match between the term and the search query. For example, in the example of Fig. 1, the extraction unit 41 extracts name terms based on the importance indicating the degree of match between the term and the search query "electric heater" entered by user U1.

[0069] The extraction unit 41 may also extract name terms based on the importance indicating the degree of agreement between the term and the description of the product. For example, in the example of Fig. 1, the extraction unit 41 extracts name terms based on the importance indicating the degree of agreement between the term and the description of product #1.

[0070] The extraction unit 41 may also extract name terms based on the importance indicating the degree of match between the term and an image showing a product. For example, in the example of Fig. 1, the extraction unit 41 extracts name terms based on the importance indicating the degree of match between the term and product image #1 showing product #1.

[0071] The extraction unit 41 may also extract name terms based on the importance indicating the distinctiveness of the term in a product. For example, in the example of Fig. 1, the extraction unit 41 extracts name terms based on the importance indicating the distinctiveness of the term in product #1.

[0072] Furthermore, the extraction unit 41 may extract, as a name term, the term with the highest importance among a plurality of terms whose similarity is equal to or greater than a predetermined threshold. For example, in the example of Fig. 1, the extraction unit 41 extracts, as a name term, the term with the highest importance from a group of similar terms #1 whose mutual similarity is equal to or greater than a predetermined threshold.

[0073] Furthermore, the extraction unit 41 may extract, as name terms, combinations of terms whose scores based on importance and similarity satisfy predetermined conditions. For example, in the example of Fig. 1, the extraction unit 41 calculates, for each combination pattern in term group #1, a score based on the importance of each included term and the similarity between the included terms, and extracts, as name terms, patterns whose scores satisfy predetermined conditions.

[0074] Furthermore, the extraction unit 41 may not extract name terms if the total number of characters in the terms linked to a product is equal to or less than a predetermined threshold. For example, in the example of Fig. 1, the extraction unit 41 does not extract name terms if the total number of characters in the terms linked to a product is equal to or less than the character limit for the display area of ​​the product name.

[0075] Furthermore, the extraction unit 41 may extract, as name terms, combinations of terms whose total number of characters is equal to or less than a predetermined threshold. For example, in the example of Fig. 1, the extraction unit 41 excludes name terms with lower importance from the group of name terms #1, and generates a name for product #1 that is equal to or less than the character limit for the name display area.

[0076] (Regarding the generation unit 42) The generation unit 42 generates a name of a product based on the name terms extracted by the extraction unit 41. For example, in the example of Fig. 1, the generation unit 42 generates a name of product #1 based on name term group #1 of product #1.

[0077] The generation unit 42 may also generate a name in which the name terms are arranged in descending order of importance. For example, in the example of Fig. 1, the generation unit 42 generates a name in which the name term group #1 is arranged in descending order of importance.

[0078] (Regarding output unit 43) The output unit 43 outputs the name generated by the generation unit 42 to the user via a predetermined e-commerce service. For example, in the example of Fig. 1, the output unit 43 outputs the name of product #1 to the user terminal 100 via e-commerce service #1.

[0079] The output unit 43 may also output the name of a product indicating each of the terms to the user via a predetermined e-commerce service. For example, in the example of Fig. 1, if the total number of characters of the terms linked to the product is equal to or less than the character limit for the display area of ​​the product name, the output unit 43 outputs the terms linked to the product, arranged in the order they were entered by the product provider, to the user terminal 100 as the product name.

[0080] [4. Information processing flow] The procedure of information processing of the information processing device 10 according to the embodiment will be described with reference to Fig. 6. Fig. 6 is a flowchart showing an example of the procedure of information processing according to the embodiment.

[0081] 6, the information processing device 10 determines whether or not a search query has been input in a predetermined e-commerce service (step S101). If the search query has not been input (step S101; No), the information processing device 10 waits until the search query is input.

[0082] On the other hand, if input of a search query is accepted (step S101; Yes), the information processing device 10 extracts name terms to be used for the product name from the terms based on the similarity between terms linked to the product corresponding to the search query (step S102). Next, the information processing device 10 generates a product name based on the name terms (step S103). Next, the information processing device 10 outputs the name to the user via a predetermined e-commerce service (step S104), and ends the process.

[0083] [5. Modifications] The above-described embodiment is merely an example, and various modifications and applications are possible.

[0084] [5-1. About the Service] In the above-described embodiment, an example has been shown in which the information processing device 10 outputs information (product names) to be output to a user via an e-commerce service, but the processing by the information processing device 10 is not limited to this example, and similar processing may be performed in any service. For example, when outputting a web page corresponding to a search query in a search service (search engine), the information processing device 10 may extract keywords to be used for generating a new title from the keywords based on the similarity between keywords included in the title (name) of the web page, generate a new title based on the extracted keywords, and output the new title to the user.

[0085] [5-2. Processing mode] Of the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, and conversely, all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information, including the processing procedures, specific names, various data, and parameters shown in the above text and drawings, can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0086] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0087] Furthermore, the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0088] [6. Effects] As described above, the information processing device 10 according to the embodiment includes an extraction unit 41, a generation unit 42, and an output unit 43. The extraction unit 41 extracts name terms to be used for the name of a product from among the terms based on the similarity between terms linked to a product corresponding to a search query entered by a user in a predetermined e-commerce service. The generation unit 42 generates a name of the product based on the name terms extracted by the extraction unit 41. The output unit 43 outputs the name generated by the generation unit 42 to the user via the predetermined e-commerce service.

[0089] As a result, the information processing device 10 according to the embodiment can generate and output the name of the product by taking into account the similarity between the terms linked to the product, and can therefore output the name of the product in an appropriate manner.

[0090] Furthermore, in the information processing device 10 according to the embodiment, for example, the extraction unit 41 further extracts name terms based on the importance and similarity of each term. The extraction unit 41 also extracts name terms based on the importance indicating the degree of match between the term and the search query. The extraction unit 41 also extracts name terms based on the importance indicating the degree of match between the term and a description of a product. The extraction unit 41 also extracts name terms based on the importance indicating the degree of match between the term and an image showing the product. The extraction unit 41 also extracts name terms based on the importance indicating the distinctiveness of the term to the product. The extraction unit 41 also extracts, as a name term, a term with the highest importance from among multiple terms whose similarity is equal to or greater than a predetermined threshold. The extraction unit 41 also extracts, from among combinations of terms, a combination whose score based on the importance and similarity satisfies a predetermined condition as a name term.

[0091] As a result, the information processing device 10 according to the embodiment can generate and output the name of a product by taking into consideration the similarity between terms linked to the product and the importance of each term, and can therefore output the name of the product in an appropriate manner.

[0092] Furthermore, in the information processing device 10 according to the embodiment, for example, the generating unit 42 generates a name in which name terms are arranged in descending order of importance.

[0093] As a result, the information processing device 10 according to the embodiment can display terms with high importance preferentially in the display area for the product name, and can therefore output the product name in an appropriate manner.

[0094] In the information processing device 10 according to the embodiment, for example, the extraction unit 41 does not extract name terms when the total number of characters in the terms linked to a product is equal to or less than a predetermined threshold. Then, the output unit 43 outputs the names of the products indicated by each of the terms to the user via a predetermined e-commerce service.

[0095] As a result, the information processing device 10 of the embodiment can display the terms set by the product provider, etc. as they are if the total number of characters of each term linked to the product is less than the character limit in the display area for the product name, thereby ensuring fidelity to the information entered by the provider regarding the product.

[0096] Furthermore, in the information processing device 10 according to the embodiment, for example, the extraction unit 41 extracts, from among combinations of terms, combinations in which the total number of characters is equal to or less than a predetermined threshold, as name terms.

[0097] As a result, the information processing device 10 according to the embodiment can generate a product name that is equal to or less than the character limit in the display area for the product name, and can therefore output the product name in an appropriate manner.

[0098] [7. Hardware Configuration] The information processing device 10 according to each of the above-described embodiments is realized, for example, by a computer 1000 configured as shown in Fig. 7. The information processing device 10 will be described below as an example. Fig. 7 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 10. The computer 1000 has a CPU 1100, a ROM 1200, a RAM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0099] The CPU 1100 operates and controls each unit based on programs 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 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0100] 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 the 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.

[0101] 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 generated data to the output devices via the input / output interface 1600.

[0102] 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 or data 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.

[0103] For example, when the computer 1000 functions as the information processing device 10, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1300 to realize the functions of the control unit 40. The HDD 1400 also stores various data in the storage device of the information processing device 10. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0104] [8. Other] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0105] Furthermore, the information processing device 10 described above can flexibly change its configuration, for example, by calling an external platform or the like using an API (Application Programming Interface) or network computing, depending on the function.

[0106] Furthermore, the term "unit" in the claims can be read as "means" or "circuit," etc. For example, an extraction unit can be read as extraction means or extraction circuit. [Explanation of symbols]

[0107] 10. Information processing equipment 20 Communications Department 30 Storage section 31 Product Information Database 32 User Information Database 33 Model Database 40 Control Unit 41 Extraction part 42 Generation part 43 Output section 100 user terminals

Claims

1. an extraction unit that extracts name terms to be used for the names of products from among terms associated with products corresponding to a search query entered by a user in a predetermined e-commerce service, based on similarities between the terms; a generation unit that generates a name of the product based on the name term extracted by the extraction unit; an output unit that outputs the name generated by the generation unit to the user via the predetermined electronic commerce service; An information processing device comprising:

2. The extraction unit Furthermore, the name terms are extracted based on the importance of each of the terms and the similarity.

2. The information processing apparatus according to claim 1, wherein:

3. The extraction unit Extracting the name terms based on the importance indicating the degree of match between the terms and the search query.

3. The information processing apparatus according to claim 2, wherein:

4. The extraction unit Extracting the name terms based on the importance indicating the degree of agreement between the terms and the product descriptions.

3. The information processing apparatus according to claim 2, wherein:

5. The extraction unit The name term is extracted based on the importance indicating the degree of match between the term and the image showing the product.

3. The information processing apparatus according to claim 2, wherein:

6. The extraction unit Extracting the name terms based on the importance indicating the distinctiveness of the terms in the product.

3. The information processing apparatus according to claim 2, wherein:

7. The extraction unit Among the plurality of terms whose similarity is equal to or greater than a predetermined threshold, the term having the highest importance is extracted as the name term.

3. The information processing apparatus according to claim 2, wherein:

8. The extraction unit Among the combinations of the terms, combinations in which the scores based on the importance and the similarity satisfy predetermined conditions are extracted as the name terms.

3. The information processing apparatus according to claim 2, wherein:

9. The generation unit Generate the name in which the name terms are arranged in descending order of importance.

3. The information processing apparatus according to claim 2, wherein:

10. The extraction unit If the total number of characters of the terms associated with the product is equal to or less than a predetermined threshold, the name term is not extracted, The output unit Outputting the names of the products indicating each of the terms to the user via the predetermined electronic commerce service.

2. The information processing apparatus according to claim 1, wherein:

11. The extraction unit Among the combinations of terms, combinations whose total number of characters is equal to or less than a predetermined threshold are extracted as the name terms.

2. The information processing apparatus according to claim 1, wherein:

12. 1. A computer-implemented information processing method, comprising: an extraction step of extracting name terms to be used for the names of products from among terms associated with products corresponding to a search query entered by a user in a predetermined e-commerce service, based on the similarity between the terms; a generating step of generating a name of the product based on the name terms extracted by the extracting step; an output step of outputting the name generated in the generation step to the user via the predetermined electronic commerce service; An information processing method comprising:

13. an extraction step of extracting name terms to be used for the names of products from among terms associated with products corresponding to a search query entered by a user in a predetermined e-commerce service, based on similarities between the terms; a generating step of generating a name of the product based on the name terms extracted by the extracting step; an output step of outputting the name generated by the generation step to the user via the predetermined electronic commerce service; An information processing program characterized by causing a computer to execute the above.

Images