Information processing system, information processing method, and program
The information processing system addresses the challenges of conventional voice recognition by using attribute-based filtering and language processing to enhance the accuracy and speed of automatic responses to inquiries, ensuring appropriate answers are derived from diverse expressions.
Patent Information
- Application Number
- JP2024163036
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-09-19
- Publication Date
- 2024-12-05
- Estimated Expiration
- 2042-03-21
AI Technical Summary
Conventional voice recognition systems struggle with accurately identifying appropriate answers to inquiries due to insufficient information, poor recognition of diverse expressions, and lengthy processing times, especially when dealing with free-spoken questions or text inputs, leading to inadequate automatic responses.
An information processing system that includes attribute information storage, voice recognition, language processing, and response specifying mechanisms to identify answer candidates based on the relationship between inquiry attributes and prepared answers, using filters to enhance relevance and speed up the response process.
The system provides more accurate and timely automatic responses by leveraging attribute-based filtering and language processing to quickly identify appropriate answers, even with diverse expressions, thus improving the responsiveness and relevance of inquiries.
Smart Images

Figure 2024169607000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an information processing system, an information processing method, and a program. [Background technology]
[0002] 2. Description of the Related Art Conventionally, there is known a technique for recognizing a user's speech and automatically responding to an inquiry. For example, the automatic voice question answering device described in Patent Document 1 uses a voice recognition engine to recognize questions in the form of free speech, and corrects the voice recognition results through discourse analysis, etc., in order to properly recognize the content of the question. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2003-263190 A Summary of the Invention [Problem to be solved by the invention]
[0004] However, in conventional technology, even if an attempt was made to identify an answer based on an inquiry input by voice, there were cases in which an appropriate answer could not be derived due to insufficient information contained in the inquiry, etc. Furthermore, when a freely spoken inquiry is subjected to speech recognition using a general-purpose speech recognition engine, there is a possibility that the content of the inquiry cannot be appropriately recognized. Furthermore, the voice recognition process and the process of identifying an answer may take a long time, which may make it impossible to respond to an inquiry promptly. Furthermore, since speakers making inquiries use a wide variety of expressions, the system may not be able to adequately handle such a wide variety of expressions. If any one of these reasons or a combination of multiple reasons occurs, it becomes difficult to provide an appropriate automated response to a voice inquiry. It should be noted that such a problem may occur not only in the case of voice recognition of a voice inquiry, but also in the case of an inquiry by text input such as chat.
[0005] An object of the present invention is to provide a technique for providing a more appropriate automatic response to an inquiry. [Means for solving the problem]
[0006] In order to achieve the above object, an information processing system according to one aspect of the present invention comprises: An information processing system including one or more information processing devices, a first attribute information storage means for storing first attribute information relating to an anticipated inquiry; a second attribute information storage means for storing second attribute information related to the response to the anticipated inquiry; An inquiry content acquisition means for acquiring the content of an inquiry; a response identifying means for identifying a response including an answer to the inquiry based on attribute information included in the content of the inquiry, the first attribute information, and the second attribute information; The present invention is characterized by comprising:
[0007] In order to achieve the above object, an information processing system according to another aspect of the present invention comprises: An information processing system including one or more information processing devices, A speech recognition means for acquiring a speech recognition result obtained by subjecting a speech for a query to speech recognition processing; a language processing means for specifying answer candidates matching the inquiry by language processing based on the meaning of the speech recognition result by the speech recognition means; an attribute processing means for extracting words contained in the query from a speech recognition result by the speech recognition means, and for identifying answer candidates matching the query based on attribute information based on the words contained in the query and attribute information based on an answer to the query; a response identifying means for identifying a response including an answer to the inquiry based on the answer candidates identified by the language processing means and the answer candidates identified by the attribute processing means; The present invention is characterized by comprising:
[0008] In order to achieve the above object, an information processing system according to another aspect of the present invention comprises: An information processing system including one or more information processing devices, a search data generating means for generating search data composed of one or more attributes associated with the answer to the anticipated inquiry based on first attribute information related to the anticipated inquiry and second attribute information related to the answer to the anticipated inquiry; An inquiry content acquisition means for acquiring the content of an inquiry; a response identifying means for identifying a response including an answer to the content of the inquiry based on attribute information of the content of the inquiry and the search data; The present invention is characterized by comprising:
[0009] In order to achieve the above object, an information processing system according to another aspect of the present invention comprises: An information processing system including one or more information processing devices, A speech recognition means for acquiring a speech recognition result obtained by subjecting a speech for a query to speech recognition processing; a filter processing means for filtering attribute information included in a speech recognition result by said speech recognition means using a filter including, as elements, first attribute information related to an expected inquiry, second attribute information related to a response to said expected inquiry, and expanded attribute information related to said first attribute information and said second attribute information; a response identifying means for identifying a response including a response to the utterance for inquiry based on a filtering process result by the filtering means; The present invention is characterized by comprising: Effect of the Invention
[0010] According to the present invention, a technique for providing a more appropriate automatic response to an inquiry can be provided. [Brief description of the drawings]
[0011] [Figure 1] 1 is a schematic diagram showing a configuration of an information processing system 1 according to the present embodiment. [Diagram 2] 2 is a schematic diagram showing a hardware configuration of an information processing device 800 constituting the terminal device 10 or the server 20. FIG. [Diagram 3] 2 is a block diagram showing a functional configuration of a terminal device 10. FIG. [Figure 4] 2 is a block diagram showing the functional configuration of the server 20. FIG. [Diagram 5] FIG. 13 is a schematic diagram illustrating an example of a response content table. [Figure 6] FIG. 13 is a schematic diagram showing an example of a connector table. [Figure 7] FIG. 13 is a schematic diagram showing an example of generation of an extraction filter. [Figure 8] FIG. 13 is a schematic diagram illustrating an example process of using an extraction filter to identify answer candidates based on attribute relevance. [Figure 9] 2 is a schematic diagram showing an example of a specific functional configuration of the information processing system 1 according to the first embodiment. FIG. [Figure 10A] 13 is a flowchart showing the flow of an automatic response process executed by the information processing system 1. [Figure 10B] 13 is a flowchart showing the flow of an extraction filter generation process executed by the information processing system 1. [Figure 11] FIG. 2 is a schematic diagram illustrating a concept of processing in an embodiment. [Figure 12A]FIG. 11 is a schematic diagram showing an example of a connector table in the second embodiment. [Figure 12B] FIG. 2 is a schematic diagram showing an example of a narrowing-down table 1. [Figure 12C] FIG. 2 is a schematic diagram showing an example of a narrowing-down table 2. [Figure 12D] FIG. 2 is a schematic diagram showing an example of a narrowing-down table 3. [Figure 13] FIG. 13 is a schematic diagram showing an example of generation of an extraction filter. [Figure 14A] FIG. 13 is a schematic diagram illustrating an example process of using an extraction filter to identify answer candidates based on attribute relevance. [Figure 14B] FIG. 13 is a schematic diagram showing an example of changes in narrowing-down tables 1 to 3 when an inquiry utterance is input multiple times. [Figure 15] 13 is a flowchart showing the flow of an automatic search process executed by the information processing system 1. [Figure 16] FIG. 13 is a block diagram showing a functional configuration of a server 20 in a third embodiment. [Figure 17] FIG. 13 is a schematic diagram showing an example of a specific functional configuration of an information processing system 1 according to a third embodiment. [Figure 18] FIG. 13 is a schematic diagram showing an example of a response content table in the third embodiment. [Figure 19] FIG. 2 is a schematic diagram showing an example of a first connector table. [Figure 20] FIG. 13 is a schematic diagram showing an example of a second connector table. [Figure 21] FIG. 13 is a schematic diagram showing an example of generating an extraction filter for a query; [Figure 22] FIG. 13 is a schematic diagram showing an example of generating an answer extraction filter. [Figure 23] FIG. 13 is a schematic diagram showing an example of a process for identifying answer candidates based on attribute relevance using a query extraction filter. [Figure 24] FIG. 13 is a schematic diagram showing an example of a process for identifying answer candidates based on attribute relevance using an answer extraction filter. [Diagram 25]13 is a flowchart showing the flow of an automatic response process executed by the information processing system 1. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0012] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. [First embodiment] The information processing system according to the present embodiment performs a process of identifying answer candidates that match the inquiry (a process of identifying using language processing) by performing speech recognition processing on an utterance for making a query, and a process of determining the relevance between attributes represented by words included in the speech recognition result of the utterance for making a query and attributes based on an expected query and answers prepared for the expected query, and performs a process of identifying answer candidates that match the uttered query based on the relevance of the attributes (a process of identifying based on the relevance of the attributes).The information processing system according to the present embodiment then identifies a final answer to the query based on the answer candidates identified by the process of identifying using language processing and the answer candidates identified by the process of identifying based on the relevance of the attributes, and outputs a response (a dialogue including the answer) to the query. Therefore, according to the information processing system according to the present embodiment, when an automatic response is made to a speech, it is possible to specify more appropriate response content while shortening the processing time.
[0013] Furthermore, in the present invention, the contents of the queries and answers are implemented to be specialized for a specific purpose (i.e., a specific target), and as a result, a combination of queries and answers appropriate for this purpose can be prepared. Then, as described below, for the prepared queries and answers, processing such as attribute classification, attribute expansion, and extraction filter generation can be performed before the query is uttered. Therefore, when a query is uttered, it is possible to quickly identify the answer.
[0014] In this embodiment, the item identified as the answer to the spoken inquiry (i.e., the result of the automatic response) is a person capable of providing an answer or content representing the answer itself (e.g., text, video, audio content, or a web page, etc.), and the person identified as the answer to the spoken inquiry will answer the inquiry based on their own knowledge, and the content identified as the answer will be provided to the user (the speaker who made the inquiry). The information processing system according to this embodiment will be specifically described below.
[0015] FIG. 1 is a schematic diagram showing the configuration of an information processing system 1 according to this embodiment. As shown in FIG. 1, the information processing system 1 includes a plurality of terminal devices 10 and a server 20. The plurality of terminal devices 10 and the server 20 are configured to be able to communicate with each other via a network 30. An information processing system 1 shown in FIG. 1 shows an example in which an information processing system according to the present invention is applied to a business system such as a call center that accepts voice inquiries via a network, and provides automatic responses to the voice inquiries.
[0016] The terminal device 10 is configured with an information processing device such as a smartphone or a PC (Personal Computer). The terminal device 10 is used by a user making an inquiry, accepts voice input representing the content of the inquiry by the user, and transmits the input voice data to the server 20. The terminal device 10 outputs to the user a response to the inquiry transmitted from the server 20 (a person capable of providing a response or content representing the response itself (for example, text, video, audio content, or a web page, etc.)).
[0017] The server 20 is configured with an information processing device such as a PC or a server computer. The server 20 receives voice data representing the inquiry content transmitted from the terminal device 10, executes voice recognition processing, and acquires text data (voice recognition result) representing the inquiry content. In this embodiment, the server 20 acquires multiple voice recognition results by executing different types of voice recognition processing in parallel. Specifically, the server 20 executes in parallel a voice recognition processing for dictation that converts the entire input voice data into text data, and a voice recognition processing for word extraction that extracts specific words included in the voice data and converts them into text data. However, the server 20 may execute one voice recognition processing (e.g., a voice recognition processing for dictation) and process one voice recognition result (e.g., a word extraction processing, etc.) to acquire multiple voice recognition results.
[0018] Furthermore, the server 20 identifies answer candidates using language processing based on the acquired voice recognition results. That is, the server 20 extracts the meaning of text data obtained by voice recognition of the user's speech using natural language processing, and identifies answer candidates that are likely to match the content of the spoken inquiry from among answers prepared in advance (here, content representing the person who will provide the answer or the answer itself). In the following, answer candidates identified using language processing will be appropriately referred to as "answer candidates by language processing".
[0019] The server 20 also extracts predetermined words from the utterance for the inquiry by speech recognition processing, and specifies answer candidates based on the relevance between the attributes represented by the words included in the utterance and the attributes of the expected inquiry and the answers prepared for the expected inquiry. That is, the server 20 expands the attributes of the expected inquiry and the answers prepared for the expected inquiry by acquiring synonyms of the words representing the attributes of the expected inquiry and the answers prepared for the expected inquiry, and determines whether the words included in the utterance for the inquiry match any of the expanded attributes using the expanded attributes (i.e., the words representing the original attributes and their synonyms) as a filter. The server 20 then specifies answer candidates corresponding to the expanded attributes that match the words included in the utterance for the inquiry. In the following, the answer candidates specified based on the relevance of the attributes will be referred to as "answer candidates based on the relevance of the attributes".
[0020] In this manner, in this embodiment, answer candidates are specified based on the relevance between the attributes represented by the words included in the query and the attributes of the expected query and the answers prepared for the expected query. Therefore, it is more likely that an answer that matches the query can be specified than when a prepared answer is specified based only on the relevance between the attributes represented by the words included in the query and the attributes of the expected query (i.e., the consistency between the content of the query and the content of the expected query). In addition, in this embodiment, the attributes of the anticipated inquiry and the answers prepared for the anticipated inquiry are expanded, and the expanded attributes (i.e., words expressing the original attributes and their similar words) are used as a filter to determine whether the expanded attributes match the words included in the inquiry utterance. Therefore, it is possible to expand the scope of the identification of relevance to the range of contents close to the inquiry utterance and contents close to the anticipated inquiry and the answers prepared for the anticipated inquiry, and therefore it is possible to identify an answer that matches the uttered inquiry while taking into account the intention of the inquiry in a broad sense.
[0021] Furthermore, the server 20 executes a process of identifying an answer by integrating the identified language processing answer candidates and the answer candidates based on attribute relevance, and identifies a final answer to the spoken inquiry. In this embodiment, if a language processing answer candidate with a certain degree of accuracy (for example, a score of the identification result by language processing is equal to or higher than a threshold) is identified as an answer candidate by language processing, the language processing answer candidate is prioritized, and if the accuracy of the language processing answer candidate is low, the attribute relevance answer candidate is selected. The server 20 then transmits the identified final answer to the terminal device 10 as voice or text data. This makes it possible to obtain high-precision speech recognition results quickly and identify an appropriate response when a query is spoken.
[0022] In this embodiment, when setting attributes to an anticipated inquiry and a response prepared for the anticipated inquiry, it is possible to set a tag or a hashtag to the data of the anticipated inquiry and the response prepared for the anticipated inquiry. In addition, in order to enable a person capable of responding to an inquiry to be identified, the server 20 can be appropriately connected to a telephone network for making calls to the person capable of responding.
[0023] [Hardware configuration] FIG. 2 is a schematic diagram showing a hardware configuration of an information processing device 800 constituting the terminal device 10 or the server 20. As shown in FIG. As shown in FIG. 2, the information processing device 800 includes a CPU (Central Processing Unit) 811, a ROM (Read Only Memory) 812, a RAM (Random Access Memory) 813, a bus 814, an input unit 815, an output unit 816, a memory unit 817, a communication unit 818, a drive 819, and an imaging unit 820.
[0024] The CPU 811 executes various processes according to a program recorded in a ROM 812 or a program loaded from a storage unit 817 to a RAM 813 . The RAM 813 also stores data and the like necessary for the CPU 811 to execute various processes.
[0025] The CPU 811, the ROM 812, and the RAM 813 are connected to one another via a bus 814. To the bus 814, an input unit 815, an output unit 816, a storage unit 817, a communication unit 818, and a drive 819 are connected.
[0026] The input unit 815 accepts various types of information input to the information processing device 800. In this embodiment, the input unit 815 includes an operation input unit 815a that accepts operation input via a display screen using a mouse, a keyboard, or the like, and an audio input unit 815b that accepts audio input using a microphone or the like. The output unit 816 is composed of a display, a speaker, etc., and outputs images and sounds. The storage unit 817 is composed of a hard disk or a dynamic random access memory (DRAM) or the like, and stores various data managed by each server. The communication unit 818 controls communications with other devices via the network.
[0027] Removable media 831, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is appropriately loaded into the drive 819. A program read from the removable media 831 by the drive 819 is installed in the storage unit 817 as necessary. The imaging section 820 is configured with an imaging device including a lens, an imaging element, etc., and captures a digital image of a subject. The above hardware configuration is the basic configuration of the information processing device 800, and it is possible to configure the information processing device 800 without some of the hardware, to include additional hardware, or to change the implementation form of the hardware. For example, the information processing device 800 can be configured without the imaging unit 820, or to include a DSP (Digital Signal Processor) for performing voice recognition processing at high speed. In addition, the information processing device 800 can be configured with a touch panel by configuring the input unit 815 with a touch sensor and arranging it over the display of the output unit 816.
[0028] [Functional configuration] Next, the functional configuration of the terminal device 10 will be described. FIG. 3 is a block diagram showing the functional configuration of the terminal device 10. As shown in FIG. As shown in FIG. 3, in the CPU 811 of the terminal device 10, an utterance receiving unit 51, an utterance data transmitting unit 52, a response receiving unit 53, and a response output unit 54 function.
[0029] The speech receiving unit 51 receives speech made as an inquiry by a user who uses the information processing system 1. The speech received by the speech receiving unit 51 is stored as voice data. The utterance data transmitting unit 52 transmits the utterance (voice data) for inquiry accepted by the utterance accepting unit 51 to the server 20. The response receiving unit 53 receives a response (Web page data, audio data, video data, or text data) transmitted from the server 20 in response to the inquiry utterance transmitted by the utterance data transmitting unit 52. The response output unit 54 outputs a response to the inquiry received by the response receiving unit 53 by voice or screen display.
[0030] Next, the functional configuration of the server 20 will be described. FIG. 4 is a block diagram showing the functional configuration of the server 20. As shown in FIG. 4, in a CPU 811 of the information processing device 800, an utterance data receiving unit 151, a preprocessing unit 152, a voice recognition processing unit 153, a language processing unit 154, a narrowing-down processing unit 155, and an integration processing unit 156 function. In addition, in a storage unit 817 of the information processing device 800, a voice recognition dictionary database (voice recognition dictionary DB) 171, a word dictionary database (word dictionary DB) 172, a response content database (response content DB) 173, and a connector database (connector DB) 174 are formed. In this embodiment, the voice recognition engines used to perform voice recognition processing include one for the purpose of dictation, which converts the entire input voice data into text data, and one for the purpose of word extraction voice recognition processing, which extracts specific words contained in the voice data and converts them into text data.
[0031] The voice recognition dictionary DB 171 stores data of various dictionaries and models (such as acoustic models, language models, and pronunciation dictionaries) used by each of a plurality of voice recognition engines. For example, the voice recognition dictionary DB 171 stores data of an acoustic model in which voice features and phoneme models are stored in association with each other, a language model in which results of statistical processing of patterns in which character strings or word strings are used as a language are stored, and a pronunciation dictionary in which words in the language model and phonemes in the acoustic model are stored in association with each other.
[0032] The word dictionary DB 172 stores a dictionary for word extraction in which words to be extracted are registered in advance. Each word in the word dictionary DB 172 is assigned a reading (pronunciation), and when a voice recognition process for extracting words is executed, the pre-registered words are extracted based on the reading (pronunciation) information. This can improve the accuracy and speed of voice recognition. The response content DB173 stores data of a response content table in which text data representing the expected inquiry content, words contained in the expected inquiry content (words representing attributes of the inquiry content), and information identifying an answer prepared for the expected inquiry (here, the name of the operator handling the inquiry or the name of the content representing the answer) are associated with each other.
[0033] FIG. 5 is a schematic diagram illustrating an example of a response content table. In FIG. 5, a cell marked with "···" indicates that some data is present or that no data is present (this also applies to the other drawings below). As shown in FIG. 5, the response content table stores a sentence (text data) expressing the expected inquiry content, an attribute (word) of the expected inquiry content, information identifying a response prepared for the expected inquiry (an operator name or a content name representing the response), and a number assigned to the response prepared for the expected inquiry, in association with each other. For example, in the second row of the response content table in FIG. 5, a sentence "I would like to register for automatic transfer" is stored as the expected inquiry content, and the words "automatic transfer" and "registration" are stored as the attributes of this inquiry content. In addition, "operator A" is stored as information identifying the response prepared for this inquiry. Note that "operator A" is assigned the number "#1". In addition, for example, in the tenth row of the response content table in FIG. 5, a sentence "I would like to open a new account" is stored as the expected inquiry content, and the words "new", "account", and "open" are stored as the attributes of this inquiry content. In addition, "opening guidance" (video file name) is stored as information identifying the response prepared for this inquiry. The "Opening Guidance" is numbered "#101."
[0034] The connector DB 174 stores data of a connector table in which words representing attributes of expected inquiry contents are associated with words representing attributes of answers prepared for the expected inquiry (here, the operator's specialty field and answering record, or the classification to which the content representing the answer belongs, etc.). Hereinafter, the attributes of the expected inquiry contents are appropriately referred to as "type A attributes", and the attributes of the answers prepared for the expected inquiry are appropriately referred to as "type B" attributes. In this embodiment, the connector DB 174 stores, as attributes of the expected inquiry contents (type A attributes), words that are explicitly included in the expected inquiry contents (explicit attributes), as well as words that are not explicitly stated (implicit attributes), such as the meaning of the expected inquiry contents itself and the name of the answer. These words are subjected to name matching and synonym unification, and each is made into a unique word (original word or original attribute). When other tables, etc. are created, the same rules as those used when generating the connector table are used when name matching and synonym unification are performed. In addition, various data generated based on the connector table (the "response specific attribute table," "response group specific attribute table," "expanded attribute table," and "extraction filter" described below) are stored in one area of RAM 813 and are also stored in connector DB 174 as appropriate.
[0035] FIG. 6 is a schematic diagram showing an example of a connector table. As shown in FIG. 6, the connector table stores, for each pair of expected inquiries and responses prepared for the expected inquiries, words representing the attributes of the expected inquiry (attributes of type A) and words representing the attributes of the responses prepared for the expected inquiries (attributes of type B) in association with each other. For example, in the second row of the connector table shown in FIG. 6, the words "automatic transfer" and "registration" are stored as attributes of the expected inquiry (attributes of type A), and the words "credit card", "debit card", "cash card", "automatic withdrawal", "transfer", etc. are stored as attributes of the responses prepared for the expected inquiries (attributes of type B). In the connector table, the implicit attributes of type A are stored on the left side of each entry. Data in one row of the connector table indicates original attributes that are preset as attributes of a pair of expected inquiries and responses prepared for the expected inquiries.
[0036] In this embodiment, in order to specify an appropriate answer from the contents of the inquiry, "attribute expansion" and "narrowing down" answers based on the expanded attributes are performed. In order to realize "attribute expansion", the following method is used: original words (original attributes) are classified into two types: words representing attributes that can uniquely specify answers prepared for the expected inquiry (response specific attributes), and words representing attributes that can specify a group of answers prepared for the expected inquiry (response group specific attributes), and each word (attribute) is expanded to a similar word, and if necessary, all words (attributes) including the expanded word (attribute) are expanded to a similar word acquired via a network (generating an "expanded attribute table" to be described later). Then, the attributes expanded by these methods are referred to, and words included in the utterance for the inquiry are filtered to specify an appropriate answer. By preparing the connector table, the response specific attribute and the response group specific attribute (specifically, the "response specific attribute table" and the "response group specific attribute table" described later), the extended attribute table, and the filter for extracting words (specifically, the "extraction filter" described later) before an inquiry is made, it becomes possible to quickly identify the answer when an inquiry is spoken. Note that data used to identify "answers prepared for expected inquiries" in the response content table, such as the response specific attribute table, the response group specific attribute table, the extended attribute table, and the filter for extracting words, are appropriately referred to as "search data".
[0037] The speech data receiving unit 151 receives an inquiry speech (voice data) transmitted from the terminal device 10. The preprocessing unit 152 performs preprocessing such as noise removal on the voice data (utterance for inquiry) received by the utterance data receiving unit 151.
[0038] The voice recognition processing unit 153 executes voice recognition processing in parallel on the voice data after the preprocessing is executed, using a plurality of voice recognition engines. Each voice recognition result acquired by the voice recognition processing is output to the language processing unit 154 and the narrowing down processing unit 155. As shown in FIG. 4, the voice recognition processing unit 153 can include a first voice recognition unit 153-1 to an n-th voice recognition unit 153-n (n is an integer of 2 or more), and the first voice recognition unit 153-1 to the n-th voice recognition unit 153-n can execute the voice recognition processing using different voice recognition engines. It can be determined according to specific implementation conditions such as the processing purpose and information processing capacity of the server 20 which voice recognition engine is used to execute the voice recognition processing in the first voice recognition unit 153-1 to the n-th voice recognition unit 153-n, and how many the first voice recognition unit 153-1 to the n-th voice recognition unit 153-n are. However, in this embodiment, the server 20 executes in parallel a voice recognition process for the purpose of dictation, which converts the entire input voice data into text data, and a word extraction voice recognition process for extracting specific words contained in the voice data and converting them into text data. The voice recognition processor 153 may also perform auxiliary processing such as filler removal as appropriate.
[0039] The language processing unit 154 extracts semantic content by language processing from the text data of the dictation result acquired by the voice recognition processing unit 153, and identifies a candidate answer (a person who will answer or a content representing the answer itself) that is likely to match the answer to the spoken content from among answers (here, a person who will answer or a content representing the answer itself) prepared in advance. At this time, the language processing unit 154 scores the degree of suitability (degree of accuracy) of the candidate answers identified from the semantic content as an answer to the inquiry, and can set the one with the highest score as the candidate answer by language processing.
[0040] The narrowing down processing unit 155 determines whether the voice recognition result of the word extraction acquired by the voice recognition processing unit 153 (i.e., the words extracted from the utterance) matches the words included in the extraction filter, and if they match, narrows down the answers (contents representing the person who will give the answer or the answer itself) prepared in advance based on the matching words included in the extraction filter. This allows answer candidates based on the relevance of attributes to be specified. Note that the narrowing down processing unit 155 generates the connector table, response specific attribute table, response group specific attribute table, enlarged attribute table, and extraction filter used in this embodiment before the user inputs the inquiry utterance.
[0041] FIG. 7 is a schematic diagram showing an example of generating an extraction filter. Note that, for ease of explanation, we will focus only on the columns in Figure 7 where specific data is shown, and will not take into account the data in the columns marked with "···" (the same applies to Figure 8). As shown in FIG. 7, when generating an extraction filter, first, a connector table is referred to, words of response specific attributes are extracted, and table-format data (hereinafter referred to as a "response specific attribute table") is generated in which the words are associated with the numbers assigned to each answer. Also, the connector table is referred to, words of response group specific attributes are extracted, and table-format data (hereinafter referred to as a "response group specific attribute table") is generated in which the numbers assigned to the answers are associated with each attribute. Furthermore, the words included in the response specific attribute table and the words included in the response group specific attribute table are expanded with synonyms. For example, the words are expanded with data of a group of synonyms prepared in advance for the words, or data of words that can be used as synonyms obtained from outside via the Internet, etc. (for example, data of words representing similar concepts obtained by referring to an ontology). Furthermore, table-format data (hereinafter referred to as an "expanded attribute table") is generated in which original words included in the response specific attribute table and the response group specific attribute table are associated with synonyms of the words. Then, an extraction filter is generated consisting of a string of words included in the expanded attribute table.
[0042] When adding a new answer candidate, the words representing the attributes of the answer candidate are matched with the words representing the existing original attributes and synonyms are unified, and the words representing the original attributes are updated. If the words representing the original attributes, including the words representing the existing original attributes, are not included in the response specific attribute table, the words representing the attributes and the answer candidate are added to the response specific attribute table, and if they are already included in the response specific attribute table, the words representing the attributes and the answer candidate are deleted from the response specific attribute table and added to the "response group specific attribute table."
[0043] FIG. 8 is a schematic diagram showing an example of a process for identifying answer candidates based on attribute relevance using an extraction filter. For example, assume that the following utterances (1) to (3) are made. Example utterance (1): "Can I manage my assets online?" Example utterance (2): "Can I use my fixed-term deposit for a card loan?" Example utterance (3): "How can I check the remaining balance of my mortgage?"
[0044] At this time, it is assumed that words expressing attributes are extracted from each example utterance as follows: Example utterance (1) "Internet" (similar word), "asset management" (original word) Example utterance (2) "Fixed term deposit" (original word), "Card loan" (original word) Example utterance (3) "Mortgage" (original word), "Balance" (original word)
[0045] In the case of utterance example (1), "net" and "asset management" match the words included in the extraction filter, and the original word "internet" corresponding to the synonym "net" is included in the response specific attribute table, so the answer prepared for the expected inquiry can be uniquely identified. That is, in the case of utterance example (1), operator B (#2) is identified from the response specific attribute table and becomes a candidate for the answer based on the relevance of attributes.
[0046] In the case of the utterance example (2), "fixed term deposit" and "card loan" match the words included in the extraction filter, and both of the original words "fixed term deposit" and "card loan" are included in the response group specific attribute table. At this time, the answers of #3, #4, and #5 (i.e., operators B, C, and D) are identified by "fixed term deposit". Also, the answers of #2 and #4 (i.e., operators B and D) are identified by "card loan". Operator D (#4) is identified by the logical product of the group of identified answers, and is set as a candidate answer based on the relevance of attributes. In this example, the answers are narrowed down to one, but if only words included in the response group specific attribute table are extracted, multiple answers may be candidates. In such a case, a response may be made that presents multiple answer candidates to the user. For example, a response may be output saying "Operator B and Operator D can answer," and a unique answer may be selected by the user's utterance. Also, if multiple answers are candidates, a response may be output that requests further utterances to uniquely identify the answer.
[0047] In the case of example utterance (3), "mortgage" and "balance" match the words included in the extraction filter, and the original words "mortgage" and "balance" are both included in the response group specific attribute table. In this case, "mortgage" identifies the answers in #2 and #4 (i.e., operators B and D). Also, "balance" identifies the answers in #4 and #5 (i.e., operators D and E). The logical product of the groups of identified answers identifies operator D (#4), which becomes a candidate answer based on attribute relevance.
[0048] Returning to FIG. 4, the integration processing unit 156 executes a process of integrating and identifying the identified answer candidates by language processing and answer candidates based on attribute relevance, and identifies a final answer to the uttered inquiry. At this time, as described above, if an answer candidate by language processing is identified that has a certain degree of accuracy (for example, an answer candidate whose score of the identification result by language processing is equal to or higher than a threshold value, etc.), the integration processing unit 156 prioritizes the answer candidate by language processing, and if the accuracy of the answer candidate by language processing is low, the integration processing unit 156 selects the answer candidate based on attribute relevance. Then, the integration processing unit 156 transmits the identified final answer to the terminal device 10 as voice or text data. Note that if the answer candidate by language processing does not have a certain degree of accuracy and an answer candidate based on attribute relevance is not identified, the integration processing unit 156 decides to output a response to the effect that an answer cannot be identified. The response content table, connector table, and extraction filter used in the server 20 are prepared and installed in the server 20 before accepting an utterance from a user (that is, before the automatic response process is executed).
[0049] [Specific functional configuration example] FIG. 9 is a schematic diagram showing an example of a specific functional configuration of the information processing system 1 in this embodiment. As shown in FIG. 9, when the voice recognition processing unit 153 performs voice recognition processing such as dictation and word extraction, the voice recognition processing unit 153 is formed with a first voice recognition unit 153-1 and a second voice recognition unit 153-2.
[0050] The first speech recognition unit 153-1 includes a dictation speech recognition unit 501, a first recognition result specification unit 502, and a first recognition result output unit 503. The dictation speech recognition unit 501 processes the speech data using a speech recognition engine for performing dictation, and converts the entire input speech data into text data. The first recognition result identification unit 502 uniquely identifies a speech recognition result from the processing result of the dictation speech recognition unit 501. For example, the first recognition result identification unit 502 identifies, from among the candidates of the speech recognition result acquired by the dictation speech recognition unit 501, the one with the highest accuracy as the speech recognition result based on a score given in the process of the speech recognition process. The first recognition result output unit 503 outputs the speech recognition result identified by the first recognition result identification unit 502 to the language processing unit 154.
[0051] The second speech recognition unit 153-2 includes a word extraction speech recognition unit 511, a second recognition result specification unit 512, and a second recognition result output unit 513. The word extraction speech recognition unit 511 processes the speech data using a speech recognition engine for performing word extraction speech recognition processing (here, this is assumed to be rule grammar speech recognition processing or speech recognition processing using DNN (Deep Neural Network)), extracts specific words contained in the speech data, and converts them into text data. The second recognition result identification unit 512 uniquely identifies a speech recognition result from the processing result of the word extraction speech recognition unit 511. For example, the second recognition result identification unit 512 identifies, as a speech recognition result, a word registered in the word dictionary DB 172 from among homonyms with different letters in the candidates of the speech recognition result acquired by the word extraction speech recognition unit 511. The second recognition result output unit 513 outputs the speech recognition result identified by the second recognition result identification unit 512 to the narrowing down processing unit 155. The speech recognition processes in the first speech recognition unit 153-1 and the second speech recognition unit 153-2 may be executed as one dictation speech recognition process (for example, speech recognition process by the dictation speech recognition unit 501), and the subsequent processes may be executed in parallel as described above. In this case, the word dictionary DB 172 is used to extract words from the text data that is the result of the dictation speech recognition process.
[0052] [Operation] Next, the operation of the information processing system 1 will be described. [Auto-Response Processing] FIG. 10A is a flowchart showing the flow of the automatic response process executed by the information processing system 1. The automatic response process is started in response to an operation being performed in the server 20 to instruct execution of the automatic response process. In addition, before the automatic response process is executed (i.e., the user inputs an inquiry), the connector table, the response specific attribute table, the response group specific attribute table, the extended attribute table, and the extraction filter (search data) are generated in advance (see FIG. 10B).
[0053] When the automatic response process is started, in step S1, the utterance receiving unit 51 of the terminal device 10 determines whether or not an utterance has been input by the user. If no speech has been input by the user, the result of step S1 is NO, and the process of step S1 is repeated. On the other hand, if a speech by the user has been input, the result of the determination in step S1 is YES, and the process proceeds to step S2.
[0054] In step S2, the speech data transmitting unit 52 of the terminal device 10 transmits the voice data of the input utterance by the user to the server 20. The transmitted voice data is received by the speech data receiving unit 151 of the server 20. In step S3, the preprocessing unit 152 of the server 20 performs preprocessing such as noise removal on the received voice data.
[0055] In step S4, the voice recognition processing unit 153 of the server 20 executes voice recognition processes (S41-1 to S43-1 and S41-2 to S43-2) in parallel on the pre-processed voice data using a plurality of voice recognition engines. Specifically, in step S41-1, the dictation speech recognition unit 501 of the server 20 processes the speech data using a speech recognition engine for performing dictation, and converts the entire input speech data into text data.
[0056] In step S42-1, the first recognition result identification unit 502 uniquely identifies the speech recognition result from the processing result of the dictation speech recognition unit 501. In step S 43 - 1 , the first recognition result output unit 503 outputs the speech recognition result identified by the first recognition result identification unit 502 to the language processing unit 154 . After step S43-1, the process proceeds to step S5.
[0057] Furthermore, in step S41-2, the word extraction speech recognition unit 511 processes the speech data using a speech recognition engine for performing word extraction speech recognition processing (here, this is rule grammar speech recognition processing or speech recognition processing using DNN), extracts specific words contained in the speech data, and converts them into text data. In step S42-2, the second recognition result identification unit 512 uniquely identifies the speech recognition result from the processing result of the word extraction speech recognition unit 511. In step S 43 - 2 , the second recognition result output unit 513 outputs the speech recognition result identified by the second recognition result identification unit 512 to the narrowing down processing unit 155 . After step S43-2, the process proceeds to step S6.
[0058] In step S5, the language processing unit 154 extracts semantic content by language processing from the text data of the dictation result acquired by the voice recognition processing unit 153, and identifies a candidate answer (a person who will answer or a content representing the answer itself) that is likely to match the answer to the spoken content from among answers (a person who will answer or a content representing the answer itself) prepared in advance. The result of identifying the candidate answers by language processing in step S5 is output to the integration processing unit 156.
[0059] In step S6, the narrowing down processing unit 155 determines whether the voice recognition result of the word extraction acquired by the voice recognition processing unit 153 (i.e., the word extracted from the utterance) matches the word included in the extraction filter, and if they match, narrows down the answers prepared in advance based on the matching word included in the extraction filter. That is, the narrowing down processing unit 155 identifies a word representing an attribute in the expanded attribute table from the word included in the extraction filter, and further identifies the answer number (i.e., the answer number included in the connector table) included in the response specific attribute table and the response group specific attribute table from the word representing the identified attribute. Then, the narrowing down processing unit 155 narrows down specific answers by referring to the response content table based on the identified answer number. As a result, answer candidates based on the attribute relevance are identified. The identification result of answer candidates based on the attribute relevance in step S6 is output to the integration processing unit 156. After steps S5 and S6, the process proceeds to step S7.
[0060] In step S7, the integration processing unit 156 determines whether or not answer candidates have been identified by language processing (for example, whether or not the score of the identification result by language processing is equal to or greater than a threshold). If answer candidates have been identified through language processing, a YES determination is made in step S7, and the process proceeds to step S9. On the other hand, if answer candidates cannot be specified by language processing, a NO determination is made in step S7, and the process proceeds to step S8. In step S8, the integration processing unit 156 executes a process of identifying answers based on the identified attribute relevance, and determines a response to the spoken inquiry (either an answer candidate based on the attribute relevance or a response indicating that no answer can be identified).
[0061] In step S9, the integration processing unit 156 outputs (transmits to the terminal device 10) a response to the inquiry as voice or text data. At this time, if a candidate for an answer by language processing is specified as a response to the inquiry, the integration processing unit 156 outputs the specified candidate for an answer by language processing, and if a candidate for an answer by language processing is not specified, the integration processing unit 156 outputs a candidate for an answer based on the attribute relevance or a response that an answer cannot be specified. The response data transmitted in step S9 is received by the response receiving unit 53 of the terminal device 10, and is output by the response output unit 54 as voice or image display. Note that the response to the inquiry output in step S9 may be a response that prompts speech to uniquely specify multiple answer candidates, or a response that outputs multiple answer candidates, in addition to a response that a uniquely specified answer or a response that an answer cannot be specified.
[0062] In step S10, the integrated processing unit 156 determines whether or not a termination condition for the automatic response process is met. The termination condition for the automatic response process can be defined as, for example, a unique response to an uttered inquiry being identified and a response being output, or an operation for terminating the inquiry being performed by the user. If the end condition for the inquiry process is not met, the result of the determination in step S10 is NO, and the process proceeds to step S1. On the other hand, if the end condition for the automatic response process is met, the answer is YES in step S10, and the automatic response process ends.
[0063] [Extraction filter generation process] FIG. 10B is a flowchart showing the flow of the extraction filter generation process executed by the information processing system 1. The extraction filter generation process is started in response to an operation for instructing execution of the extraction filter generation process being performed in the server 20. A series of search data is generated by the extraction filter generation process. When the extraction filter generation process is started, in step S21, the narrowing-down processing unit 155 acquires the expected inquiry content and attributes of the answers prepared for the expected inquiry. These attributes can be acquired from words included in the expected inquiry content and the answers prepared for the expected inquiry, or from preset attributes, etc.
[0064] In step S22, the narrowing-down processing unit 155 performs name matching and synonym unification of words expressing attributes. In step S23, the narrowing-down processing unit 155 generates a connector table by associating words representing attributes of the anticipated inquiry content (type A attributes) with words representing attributes of answers prepared for the anticipated inquiry (type B attributes).
[0065] In step S24, the narrowing-down processing unit 155 classifies the original words (original attributes) in the connector table into two categories: words that represent attributes that can uniquely identify a response prepared for an anticipated inquiry (response-specific attributes), and words that represent attributes that can identify a group of responses prepared for an anticipated inquiry (response-group-specific attributes).
[0066] In step S25, the narrowing-down processing unit 155 generates a response specific attribute table and a response group specific attribute table based on the classified response specific attributes and response group specific attributes. In step S26, the narrowing-down processing unit 155 expands the words included in the response specific attribute table and the words included in the response group specific attribute table into synonyms.
[0067] In step S27, the narrowing-down processing unit 155 generates an expanded attribute table in which the original words included in the response specific attribute table and the response group specific attribute table are associated with synonyms of the original words. In step S28, the narrowing-down processing unit 155 generates an extraction filter made up of a word string included in the expanded attribute table. After step S28, the extraction filter generation process ends.
[0068] As described above, in the information processing system 1 of the present embodiment, answer candidates are specified based on the relevance between the attributes represented by the words included in the inquiry utterance and the attributes of the expected inquiry and the answer prepared for the expected inquiry. In addition, a connector table, a response specific attribute table, a response group specific attribute table, an expanded attribute table, and an extraction filter (search data) are prepared before an inquiry is made. That is, as attributes of the expected inquiry content, words explicitly included in the expected inquiry content (explicit attributes) and words not explicitly stated (implicit attributes) such as the meaning of the expected inquiry content itself and the name of the answer are used, and a connector table is generated together with the attributes of the answer prepared for the expected inquiry. In addition, the attributes of the expected inquiry and the answer prepared for the expected inquiry are expanded to synonyms, and an extraction filter consisting of words representing the original attributes and their synonyms is generated. In addition, a predetermined word is extracted from the utterance for the inquiry by voice recognition processing, and it is determined whether or not the words extracted from the utterance match the words included in the extraction filter. Then, when the words extracted from the utterance match the words included in the extraction filter, the information processing system 1 narrows down the answers (the person who will answer or the content representing the answer itself) prepared in advance based on the matching words included in the extraction filter. This identifies answer candidates based on the relevance of attributes. The information processing system 1 also executes extraction of semantic content by language processing on text data of the dictation result obtained by processing the utterance with voice recognition, and identifies answer candidates (the person who will answer or the content representing the answer itself) that are likely to match the answer to the uttered content from among the answers (the person who will answer or the content representing the answer itself) prepared in advance. Furthermore, the information processing system 1 executes processing to integrate and identify the answer candidates by the language processing identified and the answer candidates based on the relevance of attributes, and identifies the final answer to the uttered inquiry.
[0069] Through such processing, in the information processing system 1, an answer to an uttered inquiry can be identified using not only an identification method based on language processing but also an identification method based on the consistency of words expressing attributes. Therefore, when an automatic response to a speech is made, it is possible to specify more appropriate response content while shortening the processing time. In addition, it is more likely that an answer that matches the spoken inquiry can be identified than when a prepared answer is identified based only on the correlation between the attributes expressed by the words contained in the query and the attributes of the expected query (i.e., the consistency between the content of the spoken query and the content of the expected query). In addition, the connector table, response specific attribute table, response group specific attribute table, extended attribute table, and extraction filter (search data) used in the process of identifying an answer to an inquiry are prepared before an inquiry is made, making it possible to identify the answer quickly when an inquiry is spoken.
[0070] In addition, when determining the consistency of words expressing attributes, an extraction filter is generated by expanding words expressing attributes based on an expected inquiry and answers prepared for the expected inquiry, and a consistency is determined with the attributes expressed by words included in the speech recognition results of the utterance for the inquiry. Therefore, even if an unexpected expression is used, such as when there is variation in expression or when words with similar meanings are used, it is possible to easily identify an answer that matches the uttered inquiry. In other words, since the scope of the identified relevance can be expanded to include contents close to the utterance of the inquiry, and contents close to anticipated inquiries and answers prepared for the anticipated inquiries, it is possible to identify an answer that matches the uttered inquiry while taking into account the broad intent of the inquiry.
[0071] [Second embodiment] Next, a second embodiment of the present invention will be described. In the first embodiment, the matter identified as the answer is a person capable of answering or content that represents the answer itself (for example, text, video, audio content, or a web page, etc.). In addition, the attributes of the anticipated inquiry and the answers prepared for the anticipated inquiry are classified into response-specific attributes that uniquely identify the answer and response group-specific attributes that identify the answers as a group, and these attributes are associated with each other and converted into data. Furthermore, by expanding the attributes, the words being spoken are filtered to identify the answer to the inquiry.
[0072] In contrast, in the present embodiment, the answer of the person in charge or a specific part of the entire content representing the answer in the first embodiment (for example, a specific part of the content of text, video, audio, or a web page, such as a paragraph, a section, a time period of a video, or a specific part of a web page) is also targeted for identification as an answer. In addition, in the present embodiment, as an identification process based on the relevance of attributes, a plurality of processes having different functions (hereinafter, appropriately referred to as "narrowing processes") are executed in parallel, and the identification results of these parallel processes and the identification results of an identification process using language processing are integrated to identify the content of the response (the content of the dialogue that induces the answer or the utterance of an attribute effective for identifying the answer). For example, as one of the narrowing processes, a narrowing process 1 is executed in which the answers are narrowed down by the words included in the latest utterance, with the whole words representing the attributes included in the original connector table as the target. In the narrowing process 1, the result of narrowing down the whole words representing the attributes included in the original connector table by the latest single utterance is output. As another type of narrowing down process, a narrowing down process 2 is executed, which narrows down the results of narrowing down the words representing the attributes included in the original connector table by a predetermined number of past utterances, using the words included in the latest utterance. In the narrowing down process 2, the results of narrowing down the words representing the attributes included in the original connector table by a predetermined number of past utterances different from the narrowing down process 2 are output. As another type of narrowing down process, a narrowing down process 3 is executed, which narrows down the results of narrowing down the words representing the attributes included in the original connector table by a predetermined number of past utterances different from the narrowing down process 2 (for example, all past utterances after the inquiry is made) using the words included in the latest utterance. In the narrowing down process 3, the results of narrowing down the words representing the attributes included in the original connector table by a predetermined number of past utterances different from the narrowing down process 2 (for example, all past utterances after the inquiry is made) are output. Then, the identification results by the narrowing down processes 1 to 3 and the identification results by the identification process using language processing are integrated by selecting them based on a selection condition set in advance, and the content of the response to the inquiry (the content of the dialogue that induces an answer or an utterance of an attribute effective for identifying the answer) is identified.
[0073] In this embodiment, narrowing-down processes 1 to 3 are used in conjunction with a determination process using language processing, and further, narrowing-down processes 1 to 3 are structured to enable autonomous dialogue with the user (automatic dialogue), thereby increasing the likelihood of identifying an appropriate answer. The main parts of the system configuration of the information processing system 1, the hardware configuration of the information processing device, and the functional configuration of the terminal device 10 and the server 20 in this embodiment are similar to those in the first embodiment, so the differences will be mainly described.
[0074] FIG. 11 is a schematic diagram showing the concept of processing in this embodiment. As shown in FIG. 11, in the information processing system 1 according to the present embodiment, the content of the response is specified by integrating the results of the identification by the narrowing-down processes 1 to 3 executed in parallel and the identification by the identification process using language processing. In this case, the narrowing-down processes 1 to 3 use the original connector table, the response specific attribute table generated from the original connector table, and the response group specific attribute table (hereinafter referred to as "connector tables") as starting points to generate narrowing-down tables 1 which are the results of the connector tables being narrowed down by the narrowing-down process 1, narrowing-down tables 2 which are the results of the narrowing-down tables 1 being narrowed down by the narrowing-down process 2, and narrowing-down tables 3 which are the results of the narrowing-down tables 2 being narrowed down by the narrowing-down process 3, thereby specifying answer candidates based on the relevance of attributes. However, for the narrowing-down tables 3, if a series of inquiries by the user reaches four or more times, the output result of the narrowing-down tables 3 becomes the input of the narrowing-down process 3 for the next inquiry, and narrowing down by the narrowing-down process 3 is performed recursively. The narrowing-down tables 1 to 3 which are the results of the narrowing-down processes 1 to 3 are included in the narrowing-down tables 1 to 3, respectively. The narrowing down tables 1 to 3 are data in a table format indicating which answers (specifically, answer numbers) each word narrowed down by the narrowing down processes 1 to 3 is related to. In the narrowing down tables 1 to 3, for example, "1" indicating that the word is related to the answer number and "0" indicating that the word is not related are stored for each word narrowed down by the narrowing down processes 1 to 3. Furthermore, if an answer candidate cannot be uniquely identified, the attributes included in the narrowing down tables 1 to 3 are updated to attributes that can narrow down the answers more than the current ones, and then handed over as input for the next stage of the narrowing down process (the input is replaced).
[0075] 11, the response specific attribute table included in the connector tables is called "response specific attribute table ATS0", the response group specific attribute table is called "response group specific attribute table ATG0", the response specific attribute table included in the narrowing down tables 1 is called "response specific attribute table ATS1", the response group specific attribute table is called "response group specific attribute table ATG1", the response specific attribute table included in the narrowing down tables 2 is called "response specific attribute table ATS2", the response group specific attribute table is called "response group specific attribute table ATG2", the response specific attribute table included in the narrowing down tables 3 is called "response specific attribute table ATS3", and the response group specific attribute table is called "response group specific attribute table ATG3". In the following description, similar notations will be used as appropriate.
[0076] [Functional configuration] In this embodiment, the functional configuration of the terminal device 10 is similar to the functional configuration of the first embodiment shown in FIG. 4. Furthermore, the functional configuration of the server 20 differs from the functional configuration of the first embodiment shown in FIG. 4 in the contents stored in the connector DB 174 and the contents of the processes executed by the narrowing-down processing unit 155 and the integration processing unit 156. Connector DB174 stores data of a connector table in which words representing attributes of anticipated inquiry content are associated with words representing attributes of answers prepared for the anticipated inquiries (here, answers from personnel capable of providing an answer, or attributes of the entire content representing the answer and parts of the content representing the answer).
[0077] FIG. 12A is a schematic diagram showing an example of a connector table in this embodiment. As shown in FIG. 12A, in the connector table, as in the first embodiment, for each pair of anticipated inquiries and answers prepared for the anticipated inquiries, words representing attributes of the anticipated inquiry content (type A attributes) and words representing attributes of the answers prepared for the anticipated inquiries (type B attributes) are stored in association with each other.
[0078] In this embodiment, the connector DB 174 stores, as attributes of the expected inquiry content (type A attributes), not only words explicitly included in the expected inquiry content (explicit attributes) but also words that are not explicitly stated (implicit attributes) such as the meaning of the expected inquiry content itself and the name of the answer. These words are subjected to name matching and synonym unification, and each is made into a unique word (original word, original attribute).
[0079] In this embodiment, a category to which the entire content representing the answer belongs and a category to which the part constituting the content representing the answer belongs are set as attributes of the content representing the answer (attributes of type B), and words representing attributes for the entire content and the part are stored in the connector table. The part constituting the content representing the answer can be any part of the entire content representing the answer that can be divided and set with attributes, and can be, for example, a part divided by paragraph, section, or time period of a video. In FIG. 12A, "answer address" indicates the location of data on a network, such as the URL (Uniform Resource Locator) of the content representing the answer or an address within a server.
[0080] In this embodiment, as in the first embodiment, in order to specify an appropriate answer from the content of the inquiry, "attribute expansion" and "narrowing down" of answers based on the expanded attributes are performed by referring to the connector table. In order to realize "attribute expansion", as in the first embodiment, a method is used in which (1) in addition to words (explicit attributes) explicitly included in the expected content of the inquiry, words (implicit attributes) that are not explicitly stated, such as the meaning of the expected content of the inquiry itself and the name of the answer, are stored in the connector table, and when generating a response specific attribute table from the connector table, a method is used in which (2) words representing attributes are expanded to predetermined synonyms, and (3) words representing attributes are expanded to synonyms acquired via a network. Then, by referring to the attributes expanded by these methods, words included in the utterance for the inquiry are filtered, and if necessary, the information processing system 1 specifies original attributes effective for narrowing down, thereby specifying an appropriate answer while carrying out a dialogue to guide the utterance.
[0081] The narrowing-down processing unit 155 acquires synonyms of attributes of the anticipated inquiry and the answers prepared for the anticipated inquiry. For example, the narrowing-down processing unit 155 acquires data of a group of synonyms prepared in advance for a word expressing an attribute, or data of words that can be used as synonyms acquired from outside via the Internet or the like (for example, data of words expressing similar concepts acquired by referring to an ontology, etc.).
[0082] Then, the narrowing-down processing unit 155 collects words (words representing the original attributes stored in the connector table) representing the attributes (type A and type B attributes) of the anticipated inquiry and the answers prepared for the anticipated inquiry, and words acquired as synonyms (synonyms of the original attributes), and generates an extraction filter for extracting associations between the anticipated inquiry and the answers prepared for the anticipated inquiry. At this time, the narrowing down processing unit 155 generates a response specific attribute table ATS0 and a response group specific attribute table ATG0 from the attributes obtained by expanding the words included in the connector table in order to generate the extraction filter. The response specific attribute table ATS0 and the response group specific attribute table ATG0, together with the connector table, constitute the connector tables.
[0083] In addition, in the narrowing down process 1, the narrowing down processing unit 155 narrows down the words expressing attributes included in the connector tables based on the words included in the latest utterance, and generates the narrowing down table 1 having elements of information indicating the association between the words expressing the narrowed down attributes and the answer numbers (for example, "1" indicates association and "0" indicates no association). Specifically, the narrowing down processing unit 155 refers to the connector tables and generates the narrowing down table 1 by the words related to any of the answer candidates related to the words included in the latest utterance. Note that the connector table has a significance as a narrowing down table before being narrowed down by the utterance.
[0084] FIG. 12B is a schematic diagram showing an example of the narrowing-down table 1. As shown in FIG. In FIG. 12B, narrowing-down table 1 stores, in correspondence with each other, words representing attributes contained in the connector table that are related to one of the candidate answers to which the words contained in the latest utterance relate, along with information indicating whether each word is related to each of the answer numbers ("1" indicating related or "0" indicating not related). For example, in Fig. 12B, for the word "minutes product" representing an attribute in the narrowing-down table 1, "1" is stored, indicating that it is related to the answers of #1, #2, and #X. Also, for the word "XX system" representing another attribute, "0" is stored, indicating that it is not related to the answer of #1.
[0085] The numbers of the answer candidates stored in the narrowing-down table 1 are narrowed down to those related to the words included in the latest utterance, so the narrowing-down table 1 is information showing the answer candidates narrowed down by the latest utterance. In addition, the narrowing-down table 1 also stores words that represent attributes related to the answer candidates, so it contains information necessary to narrow down the answer candidates by the next utterance. At this time, the narrowing-down processing unit 155 generates a response specific attribute table ATS1 and a response group specific attribute table ATG1 from the attributes included in the narrowing-down table 1. The response specific attribute table ATS1 and the response group specific attribute table ATG1, together with the narrowing-down table 1, constitute the narrowing-down tables 1.
[0086] The narrowing-down processing unit 155 determines whether or not an answer candidate can be uniquely identified by a word included in the latest utterance, based on the narrowing-down table 1 generated in the narrowing-down processing 1. If an answer candidate can be uniquely identified, the answer candidate is used to determine an answer candidate based on attribute relevance.
[0087] Furthermore, when the narrowing-down processing unit 155 cannot uniquely identify answer candidates based on the words included in the latest utterance based on the narrowing-down table 1 generated in the narrowing-down processing 1, it performs a dialogue to induce the user to speak of attributes that can further narrow down answers (i.e., attributes that are effective in identifying answers). Specifically, the narrowing-down processing unit 155 adopts attributes that can narrow down answers more than at present (i.e., attributes that can uniquely identify answers or attributes that reduce answer candidates more than at present) among attributes whose elements in the column in the narrowing-down table 1 include "1" as attributes to be presented to the user as information for narrowing down. Furthermore, the narrowing-down processing unit 155 updates attributes included in the narrowing-down table 1 to those that can narrow down answers more than at present. That is, the narrowing-down processing unit 155 updates the narrowing-down table 1 by excluding words that are related to all of the answer candidates related to the words included in the latest utterance (i.e., attributes that are not effective in identifying answers) and leaving words that are related to some of the answer candidates related to the words included in the latest utterance (i.e., attributes that are effective in identifying answers). Specifically, the narrowing-down processing unit 155 identifies a group of answers in the narrowing-down table 1 that are related to the words included in the latest utterance, deletes attributes of columns in which all elements of the table corresponding to the identified group of answers are "1", and leaves attributes of columns other than those that have at least one element that is "1", thereby updating the narrowing-down table 1. In addition, in accordance with the update of the narrowing-down table 1, the response specific attribute table ATS1 and the response group specific attribute table ATG1 of the narrowing-down tables 1 are also updated, and the updated narrowing-down tables 1 are passed as input to the narrowing-down processing 2. By performing such processing, the user can be prompted to speak attributes that are effective for narrowing down answers from the system.
[0088] Furthermore, in the narrowing down process 2, the narrowing down processing unit 155 receives the narrowing down tables 1 as input, narrows down the words expressing attributes included in the updated narrowing down table 1 based on the words included in the latest utterance, and generates the narrowing down table 2 having elements of information indicating the association between the words expressing the narrowed down attributes and the answer numbers (for example, "1" indicates association and "0" indicates no association). Specifically, the narrowing down processing unit 155 refers to the narrowing down table 1 and generates the narrowing down table 2 by the words related to any of the answer candidates related to the words included in the latest utterance.
[0089] FIG. 12C is a schematic diagram showing an example of the narrowing-down table 2. As shown in FIG. In FIG. 12C, narrowing-down table 2 stores, in correspondence with each other, words expressing attributes included in narrowing-down table 1 that are related to one of the candidate answers to which the words included in the latest utterance relate, along with information indicating whether each word is related to each of the answer numbers ("1" indicating related or "0" indicating not related). For example, in Fig. 12C, for the word "XX system" representing an attribute in the narrowing-down table 2, "1" is stored, indicating that it is related to the answers of #2 and #X. Also, for the word "remote conference" representing another attribute, "0" is stored, indicating that it is not related to the answer of #2.
[0090] The numbers of the answer candidates stored in the narrowing-down table 2 are narrowed down to those related to the words included in the latest utterance and the previous utterance, so the narrowing-down table 2 is information showing the answer candidates narrowed down by the latest utterance and the previous utterance. In addition, the narrowing-down table 2 also stores words that represent attributes related to the answer candidates, so it contains information necessary to narrow down the answer candidates by the next utterance. At this time, the narrowing-down processing unit 155 generates a response specific attribute table ATS2 and a response group specific attribute table ATG2 from the attributes included in the narrowing-down table 2. The response specific attribute table ATS2 and the response group specific attribute table ATG2, together with the narrowing-down table 2, constitute the narrowing-down tables 2.
[0091] Furthermore, the narrowing-down processing unit 155 determines whether or not answer candidates can be uniquely identified by the words included in the latest utterance, based on the narrowing-down table 2 generated in the narrowing-down processing 2. If answer candidates can be uniquely identified, the answer candidates are used to determine answer candidates based on attribute relevance.
[0092] Furthermore, when the narrowing-down processing unit 155 cannot uniquely identify answer candidates based on the words included in the latest utterance based on the narrowing-down table 2 generated in the narrowing-down processing 2, it performs a dialogue to induce the user to speak of attributes that can further narrow down answers (i.e., attributes that are effective in identifying answers). Specifically, the narrowing-down processing unit 155 adopts attributes that can narrow down answers more than at present (i.e., attributes that can uniquely identify answers or attributes that reduce answer candidates more than at present) among attributes whose column elements in the narrowing-down table 2 include "1" as attributes to be presented to the user as information for narrowing down. Furthermore, the narrowing-down processing unit 155 updates attributes included in the narrowing-down table 2 to attributes that can narrow down answers more than at present. That is, the narrowing-down processing unit 155 updates the narrowing-down table 2 by excluding words that are related to all of the answer candidates related to the words included in the latest utterance (i.e., attributes that are not effective in identifying answers) and leaving words that are related to some of the answer candidates related to the words included in the latest utterance (i.e., attributes that are effective in identifying answers). Specifically, the narrowing-down processing unit 155 updates the narrowing-down table 2 by identifying a group of answers related to the words included in the latest utterance in the narrowing-down table 2, deleting attributes of columns in which all elements of the table corresponding to the identified group of answers are "1", and leaving attributes of columns in which at least one element is "1" among other attributes. At this time, the narrowing-down table 2 is updated by excluding the words included in the latest utterance. In addition, in accordance with the update of the narrowing-down table 2, the response specific attribute table ATS2 and the response group specific attribute table ATG2 of the narrowing-down tables 2 are also updated, and the updated narrowing-down tables 2 are delivered as input to the narrowing-down processing 3. By performing such processing, the user can be prompted to speak attributes that are effective for narrowing down answers from the system.
[0093] Furthermore, in the narrowing down process 3, the narrowing down processing unit 155 uses the narrowing down tables 2 as input from the start of the inquiry to the third utterance, narrows down the words expressing the attributes included in the updated narrowing down table 2 based on the words included in the latest utterance, and generates the narrowing down table 3 whose elements are information indicating the association between the words expressing the narrowed down attributes and the answer number (for example, "1" indicates association and "0" indicates no association). Specifically, the narrowing down processing unit 155 refers to the narrowing down table 2 and generates the narrowing down table 3 by the words related to any of the answer candidates related to the words included in the latest utterance.
[0094] Furthermore, in the narrowing down process 3, from the fourth utterance onwards from the start of the inquiry, the narrowing down processing unit 155 inputs the narrowing down tables 3 updated in the previous narrowing down process 3, narrows down the words expressing the attributes included in the updated narrowing down table 3 based on the words included in the latest utterance, and generates the narrowing down table 3 whose elements are information indicating the association between the words expressing the narrowed down attributes and the answer number (for example, "1" indicates association and "0" indicates no association). Specifically, the narrowing down processing unit 155 refers to the narrowing down table 2 and generates the narrowing down table 3 by the words associated with any of the answer candidates associated with the words included in the latest utterance.
[0095] FIG. 12D is a schematic diagram showing an example of the narrowing-down table 3. As shown in FIG. In FIG. 12D, narrowing-down table 3 stores, in correspondence with each other, words representing attributes that are the result of narrowing down the words representing attributes contained in the input narrowing-down table 2 or narrowing-down table 3 to words that are related to some of the answer candidates to which the words contained in the latest utterance are related, along with information indicating whether each word is related to each answer number ("1" indicating related or "0" indicating not related). For example, in FIG. 12D, for the word "remote conference" representing an attribute in narrowing-down table 3, "1" is stored, indicating that it is related to the answer of #X.
[0096] The numbers of the answer candidates stored in the narrowing-down table 3 are narrowed down to those related to the words contained from the start of the inquiry to the latest utterance, so the narrowing-down table 3 is information showing the answer candidates narrowed down by the latest utterance from the start of the inquiry. In addition, the narrowing-down table 3 also stores words that represent attributes related to the answer candidates, so it contains information necessary to narrow down the answer candidates by the next utterance. At this time, the narrowing-down processing unit 155 generates a response specific attribute table ATS3 and a response group specific attribute table ATG3 from the attributes included in the narrowing-down table 3. The response specific attribute table ATS3 and the response group specific attribute table ATG3, together with the narrowing-down table 3, constitute the narrowing-down tables 3.
[0097] Furthermore, the narrowing-down processing unit 155 determines whether or not answer candidates can be uniquely identified by the words included in the latest utterance, based on the narrowing-down table 3 generated in the narrowing-down process 3. If answer candidates can be uniquely identified, the answer candidates are used to determine answer candidates based on attribute relevance.
[0098] Furthermore, when the narrowing-down processing unit 155 cannot uniquely identify answer candidates based on the words included in the latest utterance based on the narrowing-down table 3 generated in the narrowing-down processing 3, it performs a dialogue to induce the user to speak of attributes that can further narrow down answers (i.e., attributes that are effective in identifying answers). Specifically, the narrowing-down processing unit 155 adopts attributes that can narrow down answers more than at present (i.e., attributes that can uniquely identify answers or attributes that reduce answer candidates more than at present) among attributes whose column elements in the narrowing-down table 3 include "1" as attributes to be presented to the user as information for narrowing down. Furthermore, the narrowing-down processing unit 155 updates attributes included in the narrowing-down table 3 to attributes that can narrow down answers more than at present. That is, the narrowing-down processing unit 155 updates the narrowing-down table 3 by excluding words that are related to all of the answer candidates related to the words included in the latest utterance (i.e., attributes that are not effective in identifying answers) and leaving words that are related to some of the answer candidates related to the words included in the latest utterance (i.e., attributes that are effective in identifying answers). Specifically, the narrowing-down processing unit 155 updates the narrowing-down table 3 by identifying a group of answers related to the words included in the latest utterance in the narrowing-down table 3, deleting attributes of columns in which all elements of the table corresponding to the identified group of answers are "1", and leaving attributes of columns in which at least one element is "1" among other attributes. At this time, the narrowing-down table 3 is updated by excluding the words included in the latest utterance. In addition, in accordance with the update of the narrowing-down table 3, the response specific attribute table ATS3 and the response group specific attribute table ATG3 of the narrowing-down tables 3 are also updated, and the updated narrowing-down tables 3 are used as the input of the narrowing-down process 3. By performing such processing, the user can be prompted to speak attributes that are effective for narrowing down answers from the system.
[0099] The narrowing-down processing unit 155 executes narrowing-down processing 1, narrowing-down processing 2, and narrowing-down processing 3 in parallel, and sequentially generates and updates narrowing-down tables 1 to 3 by narrowing-down processing 1 to 3. Then, the narrowing-down processing unit 155 outputs the results of identifying answer candidates by narrowing-down processing 1 to 3 to the integration processing unit 156. Note that the narrowing-down processing 1 is executed from the first utterance in the inquiry, the narrowing-down processing 2 is executed from the second utterance in the inquiry (utterance in response to the first dialogue performed by the system to narrow down answers), and the narrowing-down processing 3 is executed from the third utterance in the inquiry (utterance in response to the second dialogue performed by the system to narrow down answers).
[0100] Here, in the narrowing down processes 1 to 3, the generation (or update) of the narrowing down tables 1 to 3 and the replacement (transfer) of the narrowing down tables that serve as inputs to the narrowing down processes 2 and 3 can take various forms that enable narrowing down the answers for each utterance, but as an example, in this embodiment, the following procedure is defined. (1) Narrowing table 1 is generated sequentially when a word is extracted by an extraction filter in the latest utterance by narrowing down the words contained in the connector table through narrowing process 1. When an answer is not uniquely identified and narrowing table 1 is updated, the input of narrowing process 2 is replaced with the updated narrowing table 1. (2) Narrowing table 1 is not updated if no words are extracted by the extraction filter in the latest utterance.
[0101] (3) Narrowing table 2 is not generated (narrowing process 2 is not executed) for an utterance immediately after initialization (immediately after narrowing tables 1 to 3 are reset). (4) For utterances other than those immediately after initialization, if there is an attribute in the narrowing-down tables 1, which are the output of the narrowing-down process 1 for the previous utterance, that matches a word extracted in the latest utterance, the narrowing-down table 2 is generated by narrowing down the words included in the narrowing-down table 1 by the narrowing-down process 2. If the answer is not uniquely identified and the narrowing-down table 2 is updated, the input of the narrowing-down process 3 is replaced with the updated narrowing-down table 2. (5) For utterances other than those immediately after initialization, the narrowing-down table 2 is not generated if there are no attributes in the narrowing-down tables 1, which are the output of the narrowing-down process 1 for the previous utterance, that match the words extracted in the latest utterance.
[0102] (6) Narrowing table 3 is not generated (narrowing process 3 is not executed) for an utterance immediately after initialization (after narrowing tables 1 to 3 are reset). (7) Narrowing table 3 is not generated (narrowing process 3 is not executed) for the second utterance after initialization (after the narrowing tables 1 to 3 are reset). (8) For utterances other than immediately after initialization and the second utterance after initialization, if there is an attribute in the narrowing-down tables 2, which are the output of the narrowing-down process 2 for the previous utterance, that matches a word extracted in the latest utterance, the narrowing-down table 3 is generated by narrowing down the words included in the narrowing-down table 2 by the narrowing-down process 2. If the answer is not uniquely identified and the narrowing-down table 3 is updated, the input of the narrowing-down process 3 is replaced with the updated narrowing-down table 3 when a subsequent utterance is made to inquire. (9) For utterances other than immediately after initialization or the second utterance after initialization, narrowing-down table 3 will not be generated if there is no attribute matching the word extracted in the latest utterance in narrowing-down tables 2 which are the output of narrowing-down process 2 for the previous utterance or in narrowing-down tables 3 which are the output of narrowing-down process 3 for the previous utterance.
[0103] FIG. 13 is a schematic diagram showing an example of generating an extraction filter. Note that, for ease of explanation, we will focus only on the columns in Figure 13 where specific data is shown, and will not take into account the data in the columns marked with "···" (the same applies to Figure 14). In addition, in the example shown in FIG. 13, for convenience of explanation, the attributes of the entire content representing the answer are illustrated as the target, but the attributes of a portion of the content representing the answer can also be handled in the same manner.
[0104] As shown in FIG. 13, when an extraction filter is generated, the narrowing-down processing unit 155 first refers to the connector DB 174, extracts words that represent attributes that can uniquely identify answers prepared for the expected inquiry, and generates table-format data (response specific attribute table ATS0) in which the words are associated with numbers assigned to each answer. The narrowing-down processing unit 155 also refers to the connector DB 174, extracts words that represent attributes that can identify a group of answers (whole or part) prepared for the expected inquiry, and generates table-format data (response group specific attribute table ATG0) in which the numbers assigned to the answers are associated with each attribute. Furthermore, the narrowing-down processing unit 155 acquires words included in the response specific attribute table ATS0 and synonyms of words included in the response group specific attribute table ATG0, and generates table-format data (expanded attribute table) in which original words included in the response specific attribute table ATS0 and the response group specific attribute table ATG0 are associated with synonyms of the words. Then, the narrowing-down processing unit 155 generates an extraction filter consisting of a word string included in the expanded attribute table.
[0105] FIG. 14A is a schematic diagram showing an example of a process for identifying answer candidates based on attribute relevance using an extraction filter. FIG. 14B is a schematic diagram showing an example of changes in narrowing-down tables 1 to 3 when an inquiry utterance is input multiple times. Note that FIG. 14A shows an example in which answer candidates are identified from words extracted by the extraction filter via the response specific attribute table ATS0 and response group specific attribute table ATG0 included in the connector tables, but answer candidates are similarly identified in the narrowing down tables 1 to 3 via the response specific attribute tables ATS1 to 3 and response group specific attribute tables ATG1 to 3. For example, assume that the following example utterance (1) is made as an utterance to start an inquiry. Example utterance (1): "I would like to know about meeting minutes products."
[0106] In this case, it is assumed that words expressing attributes are extracted from the utterance of example utterance (1) as follows: Extracted words: "Minutes product" (original words)
[0107] In the case of utterance example (1), "minutes product" matches the words included in the extraction filter, and the original word "minutes product" is included in the response group specific attribute table ATG0. At this time, answers #1, #2, and #X are identified by "minutes product", and narrowing down process 1 generates narrowing down table 1 (see "Result of utterance example (1)" in FIG. 14B). Specifically, attributes associated with each answer are acquired in the identified answer groups #1, #2, and #X. Then, narrowing down table 1, response specific attribute table ATS1, and response group specific attribute table ATG1 are generated, whose elements are information indicating the association between the word representing the acquired attribute and the number of each answer.
[0108] In this case, since the answer cannot be uniquely specified, the narrowing-down table 1 is referenced, and among the attributes whose column elements in the narrowing-down table 1 contain "1", attributes that can narrow down the answers more than at present (i.e., attributes that can uniquely specify the answer or attributes that reduce the number of answer candidates more than at present) are adopted as attributes to be presented to the user as information for narrowing down. In addition, in the narrowing-down table 1, words that are associated with all of the answer candidates related to the words included in the latest utterance (i.e., attributes that are not effective in specifying the answer) are excluded, and the narrowing-down table 1 is updated by leaving words that are associated with some of the answer candidates related to the words included in the latest utterance (i.e., attributes that are effective in specifying the answer). This executes a dialogue that induces the user to speak of attributes that are effective in specifying the answer. Specifically, referring to Narrowing Table 1, the answers to #1, #2, and #X can be narrowed down more than the current answers if either "XX system" or "remote conference" is spoken, so the following utterance is output to the user: "If you can say "XX system" or "remote conference", we can give you an answer."
[0109] When the information processing system 1 performs a dialogue inviting the user to speak an utterance of an attribute effective for identifying an answer, narrowing-down processes 1 and 2 are executed based on the words included in the utterance, and narrowing-down tables 1 and 2 are generated. As a result, the answer candidates are further narrowed down. For example, it is assumed that after the information processing system 1 has performed a dialogue to induce an utterance of an attribute effective for identifying an answer, the user makes an utterance such as the following additional utterance example as a second utterance. Additional utterance example (1) "I'm interested in the XX system"
[0110] In the additional utterance example (1), "XX system" matches the words included in the extraction filter. In the narrowing process 1, the same process as in the case of the "minutes product" described above is executed for the additional utterance example (1). On the other hand, in the narrowing down process 2, the original word "XX system" is included in the response group specific attribute table ATG1. At this time, the responses #2 and #X are identified by "minutes product", and the narrowing down table 2 is generated by the narrowing down process 2 (see "Result of additional utterance example (1)" in FIG. 14B). Specifically, in the identified response groups #2 and #X, attributes associated with each response are acquired. Then, the narrowing down table 2, the response specific attribute table ATS2, and the response group specific attribute table ATG2 are generated, whose elements are information indicating the association between the word representing the acquired attribute and the number of each response.
[0111] In this case, since the answer cannot be uniquely identified, narrowing-down table 2 is referenced, and among the attributes whose column elements in narrowing-down table 2 contain "1", attributes that can narrow down the answers more than at present (i.e., attributes that can uniquely identify the answer or attributes that reduce the number of answer candidates more than at present) are adopted as attributes to be presented to the user as information for narrowing down. Also, narrowing-down table 2 is updated by excluding words in the latest utterance that are associated with all of the related answer candidates (i.e., attributes that are not effective in identifying an answer) and leaving words in the latest utterance that are associated with some of the related answer candidates (i.e., attributes that are effective in identifying an answer). This allows a dialogue to be executed that prompts the user to speak about attributes that are effective in identifying an answer. Specifically, by referring to Narrowing Table 2, the answer to #2 and #X can be uniquely narrowed down if "remote conference" is spoken, so the following utterance is output to the user: "If you say 'remote conference', we can answer."
[0112] When the information processing system 1 performs a dialogue inviting the user to speak an utterance of an attribute effective for identifying an answer, narrowing-down processes 1 to 3 are executed based on the words included in the utterance, and narrowing-down tables 1 to 3 are generated. As a result, answer candidates are uniquely narrowed down in narrowing-down table 3. For example, it is assumed that after the information processing system 1 has performed a dialogue to induce an utterance of an attribute effective for identifying an answer, the user utters an utterance such as the following additional utterance example as a third utterance. Additional utterance example (2) "What is a remote meeting?"
[0113] In the additional utterance example (2), "remote conference" matches the word included in the extraction filter. For the additional utterance example (2), in the narrowing down processes 1 and 2, the same processes as those in the above-mentioned cases of "minutes product" and "XX system" are executed. On the other hand, in the narrowing-down process 3, the original word "remote conference" is included in the response group identification attribute table ATG2. In this case, the answer of #X is identified by "remote conference", and the narrowing-down table 3 is generated by the narrowing-down process 3 (see "Result of additional utterance example (2)" in FIG. 14B). As a result, in the example shown here, the answer candidates are uniquely narrowed down in the narrowing-down table 3.
[0114] The integration processing unit 156 executes a process of integrating and identifying the answer candidates determined by the identified language processing and the results of the narrowing down processes 1 to 3, and identifies the response content to the uttered inquiry (the final answer or the content of the dialogue that induces the utterance of an attribute effective in identifying the answer) as the final answer. In this embodiment, the integration processing unit 156 identifies the final answer using the following selection criteria.
[0115] That is, the integration processing unit 156 (i) If a candidate answer generated by language processing is identified as having a certain degree of accuracy (for example, a score of the identified result generated by language processing is above a threshold), the candidate answer generated by language processing is selected as the final answer. (ii) When no candidate answer with a certain degree of certainty has been identified through language processing, if candidate answers based on attribute relevance are narrowed down to one answer in Narrowing Table 1, Narrowing Table 2, or Narrowing Table 3, then that narrowed down answer is selected as the final answer. (iii) If the answer candidate based on attribute relevance is not the result of (ii), and the answer candidate generated by language processing is included among the answer candidates in Narrowing Table 1, Narrowing Table 2, or Narrowing Table 3, the answer candidate generated by language processing is selected as the final answer. (iv) If the answer candidate based on the attribute relevance is not the result of (iii), refer to the narrowing down tables that had a narrowing down effect on the latest utterance (i.e., the results of narrowing down processes 1 to 3 that were able to narrow down the answers), generate a message that encourages the user to speak next including an attribute that has a narrowing down effect (an attribute that reduces the number of answer candidates from the current number), and use this as a response. However, if there are multiple narrowing down tables that had a narrowing down effect on the latest utterance, refer to the response group specific attribute table that is the output of the narrowing down process with a higher number.
[0116] [Operation] Next, the operation of the information processing system 1 will be described. [Automatic search process] FIG. 15 is a flowchart showing the flow of the automatic search process executed by the information processing system 1. The automatic search process is started in response to an operation being performed in the server 20 to instruct the execution of the automatic search process. In the flowchart shown in FIG. 15, the processes in steps S1 to S5 are similar to the automatic response process in the first embodiment shown in FIG. 10A. In this embodiment, prior to the execution of the automatic search process, the connector table, response specific attribute table ATS0, and response group specific attribute table ATG0 (connector tables) used in the narrowing down process 1 are set.
[0117] In step S6A, narrowing-down processing unit 155 executes narrowing-down processing 1 to 3 in parallel, and outputs each of the identification results to integration processing unit 156. In step S7A, the integration processing unit 156 determines whether or not answer candidates have been specified by language processing (whether or not answer candidates having a certain degree of accuracy have been specified). If answer candidates can be identified through linguistic processing, a YES determination is made in step S7A, and the process proceeds to step S13A. On the other hand, if answer candidates cannot be specified by language processing, a NO determination is made in step S7A, and the process proceeds to step S8A.
[0118] In step S8A, the integration processing unit 156 specifies answer candidates based on the results of the narrowing down processes 1 to 3, using preset selection criteria. In step S9A, the integration processing unit 156 determines whether or not answer candidates have been uniquely identified through the narrowing-down processes 1 to 3. If answer candidates can be uniquely identified by narrowing down processes 1 to 3, a YES determination is made in step S9A, and the process proceeds to step S13A. On the other hand, if answer candidates have not been uniquely identified through the narrowing down processes 1 to 3, a NO determination is made in step S9A, and the process proceeds to step S10A.
[0119] In step S10A, narrowing-down processing unit 155 updates narrowing-down tables 1 to 3. As a result, the attributes included in narrowing-down tables 1 to 3 are updated to those that can narrow down answers more than at present. Note that if narrowing-down tables 1 to 3 have not been narrowed down by words included in the latest utterance (answer candidates have not decreased from the current number), the narrowing-down tables to which the narrowing-down tables belong are not updated (the process of step S10A is skipped). In step S11A, the narrowing-down processing unit 155 determines the dialogue content that induces the utterance of the attribute. In step S12A, the narrowing-down processing unit 155 replaces (transfers) the updated narrowing-down tables as inputs for other narrowing-down processes. Note that if the narrowing-down tables 1 to 3 have not been narrowed down by the words included in the latest utterance (the number of answer candidates has not decreased from the current number), the narrowing-down tables to which the narrowing-down table belongs are not replaced (transferred) as inputs for other narrowing-down processes (the process of step S12A is skipped).
[0120] In step S13A, the integration processing unit 156 outputs (transmits to the terminal device 10) a response to the inquiry as voice or text data. At this time, if a candidate answer by language processing is specified as a response to the inquiry, the integration processing unit 156 outputs the specified candidate answer by language processing, and if a candidate answer by language processing is not specified, outputs a candidate answer based on the relevance of attributes or dialogue content inviting the speech of attributes. The response data transmitted in step S13A is received by the response receiving unit 53 of the terminal device 10, and is output by the response output unit 54 as voice or image display. At this time, if multiple candidate answers have been narrowed down, these multiple candidate answers may be output as final answers.
[0121] In step S14A, the integrated processing unit 156 determines whether or not a termination condition for the automatic response process is met. The termination condition for the automatic response process can be defined as, for example, a unique response to an uttered inquiry being identified and a response being output, or an operation for terminating the inquiry being performed by the user. If the end condition for the inquiry process is not met, the result of the determination in step S14A is NO, and the process proceeds to step S1. On the other hand, if the end condition for the automatic response process is met, the result of the determination in step S14A is YES, and the automatic search process ends.
[0122] As described above, in the information processing system 1 according to this embodiment, multiple narrowing down processes 1 to 3 having different functions are executed in parallel as a process for selecting answer candidates based on attribute relevance, and the content of the response is identified by integrating the identification results of these parallel processes and the identification results of the identification process using language processing. Then, when an answer cannot be identified by a single utterance for inquiry, the information processing system 1 automatically narrows down attributes effective for identifying the answer, and autonomously carries out a dialogue that induces a meaningful utterance by the user. This can increase the likelihood that a suitable answer will be identified as an answer candidate based on attribute relevance.
[0123] In addition, in the information processing system 1 of this embodiment, in addition to the entire content representing the answer being identified as the answer, a part of the content (for example, a paragraph, a section, or a time period of a video) is also identified as the answer. This makes it possible to identify a part of an appropriate answer, even if the appropriate answer is included as part of the content of the answer prepared for an anticipated inquiry, as the answer, thereby further increasing the possibility of identifying an appropriate answer. Therefore, according to the information processing system 1, when an automatic response to a speech is made, it is possible to specify more appropriate response content while shortening the processing time.
[0124] [Third embodiment] Next, a third embodiment of the present invention will be described. The information processing system 1 of this embodiment differs from the information processing system 1 of the first embodiment in that it does not perform identification of answer candidates through language processing, but instead executes in parallel a first identification process for identifying answer candidates based on attribute relevance using an inquiry extraction filter generated from attributes of an anticipated inquiry, and a second identification process for identifying answer candidates based on attribute relevance using an answer extraction filter generated from attributes of answers prepared for the anticipated inquiry, and outputs the answer identified in the first identification process or the second identification process as the final answer.
[0125] The main parts of the present embodiment, such as the system configuration of the information processing system 1, the hardware configuration of the information processing device, and the functional configuration of the terminal device 10, are similar to those of the first embodiment, so differences will be mainly described. The following mainly describes the functional configuration of the server 20 and the flowchart of the automatic response process, which are different from the first embodiment.
[0126] [Functional configuration] FIG. 16 is a block diagram showing the functional configuration of the server 20 in this embodiment. FIG. 17 is a schematic diagram showing an example of a specific functional configuration of the information processing system 1 in this embodiment. The response content DB 173 stores data of a response content table in which text data (here, the name of the person in charge) representing the anticipated inquiry content is associated with a response (here, the telephone number of the person in charge) prepared for the anticipated inquiry.
[0127] FIG. 18 is a schematic diagram showing an example of a response content table in this embodiment. As shown in FIG. 18, the response content table of this embodiment stores, in association with each other, text data representing the anticipated inquiry content (name of the person in charge), a response prepared for the anticipated inquiry (phone number of the person in charge), a number assigned to the anticipated inquiry, and a number assigned to the response prepared for the anticipated inquiry.
[0128] Connector DB 174 stores data of a first connector table corresponding to anticipated inquiries, and data of a second connector table corresponding to responses prepared to the anticipated inquiries. FIG. 19 is a schematic diagram showing an example of the first connector table, and FIG. 20 is a schematic diagram showing an example of the second connector table.
[0129] As shown in Fig. 19, the first connector table stores a number assigned to an expected inquiry, text data representing the expected inquiry (i.e., the name of the person in charge), a word representing an attribute of the expected inquiry (such as the name of the person in charge), and a number assigned to a response prepared for the expected inquiry (the person in charge's phone number), all in association with each other. For example, the second row of the first connector table shown in Fig. 19 stores the word "Kono" (surname) as an attribute of the expected inquiry for "Kono Saburo" (name) representing the expected inquiry.
[0130] Also, as shown in Fig. 20, the second connector table stores, for each anticipated inquiry (i.e., person in charge), a word representing the response ability and attributes of the person in charge (department, position, product in charge, etc.) and a number assigned to the answer prepared for the anticipated inquiry in association with each other. For example, the second row of the second connector table shown in Fig. 20 stores a word representing the attributes of the answer prepared for the anticipated inquiry (head office / development department / development section / ··· / XX product / ···) and a number assigned to the answer prepared for the anticipated inquiry.
[0131] 16 and 17, the server 20 in this embodiment does not identify answer candidates by language processing, and therefore does not include the language processing unit 154 and the integration processing unit 156. In addition, the server 20 in this embodiment does not execute dictation speech recognition processing, but executes two word extraction speech recognition processes in parallel, and therefore includes a word extraction speech recognition unit 501A instead of the dictation speech recognition unit 501 in the first embodiment shown in FIG.
[0132] Here, one of the two word extraction speech recognition processes is a speech recognition process for extracting words contained in anticipated inquiries, and the other is a speech recognition process for extracting words contained in answers prepared to the anticipated inquiries. Therefore, in FIG. 17, the dictionary data of word dictionary DB 172 referred to by word extraction speech recognition unit 501A has registered therein words contained in anticipated inquiries, and the dictionary data of word dictionary DB 172 referred to by word extraction speech recognition unit 511 has registered therein words contained in responses prepared to the anticipated inquiries.
[0133] In addition, the narrowing-down processing unit 155 in Figures 16 and 17 executes a first identification process to identify answer candidates based on attribute relevance using an inquiry extraction filter generated from attributes of the anticipated inquiry, and executes a second identification process to identify answer candidates based on attribute relevance using an answer extraction filter generated from attributes of answers prepared for the anticipated inquiry. Then, from the results of the first and second identification processes executed by the narrowing-down processing unit 155, an answer to the question is uniquely identified and is set as the final answer.
[0134] FIG. 21 is a schematic diagram showing an example of generating an extraction filter for a query. Note that, for ease of explanation, we will focus only on the columns in Figure 20 where specific data is shown, and will not take into account the data in the columns shown with "···" (the same applies to Figures 22 to 25). As shown in FIG. 21, when generating an inquiry extraction filter, the narrowing-down processing unit 155 first refers to the first connector table of the connector DB 174, extracts words of response specific attributes, and generates table-format data (response specific attribute table) in which the words are associated with numbers assigned to each answer. The narrowing-down processing unit 155 also refers to the first connector table of the connector DB 174, extracts words of response group specific attributes, and generates table-format data (response group specific attribute table) in which the numbers assigned to the answers are associated with each attribute. Furthermore, the narrowing-down processing unit 155 expands the words included in the response specific attribute table and the words included in the response group specific attribute table with synonyms. For example, the words are expanded with data of a group of synonyms prepared in advance for the words, or data of words that can be used as synonyms acquired from the outside via the Internet, etc. (for example, data of words representing similar concepts acquired with reference to an ontology). Furthermore, the narrowing-down processing unit 155 generates table-format data (expanded attribute table) in which original words included in the response specific attribute table and the response group specific attribute table are associated with synonyms of the words. Then, the narrowing-down processing unit 155 generates an extraction filter for inquiry made up of a word string contained in the expanded attribute table.
[0135] FIG. 22 is a schematic diagram showing an example of generating an answer extraction filter. In this embodiment, an answer extraction filter is generated from attributes of answers prepared for anticipated inquiries, separate from an inquiry extraction filter generated from attributes of anticipated inquiries. As shown in FIG. 22, when an answer extraction filter is generated, the narrowing-down processing unit 155 first refers to the second connector table of the connector DB 174, extracts words of answer specific attributes, and generates table-format data (answer specific attribute table) in which the words are associated with the numbers assigned to each answer. The narrowing-down processing unit 155 also refers to the second connector table of the connector DB 174, extracts words of answer group specific attributes, and generates table-format data (answer group specific attribute table) in which the numbers assigned to the answers are associated with each attribute. Furthermore, the narrowing-down processing unit 155 expands the words included in the answer specific attribute table and the words included in the answer group specific attribute table with synonyms. For example, the words are expanded with data of synonyms prepared in advance for the words, or data of words that can be used as synonyms obtained from the outside via the Internet, etc. (for example, data of words representing similar concepts obtained by referring to an ontology). Furthermore, the narrowing-down processing unit 155 generates table-format data (expanded attribute table) in which original words included in the response specific attribute table and the response group specific attribute table are associated with synonyms of the words. Then, the narrowing-down processing unit 155 generates an answer extraction filter made up of a word string contained in the expanded attribute table.
[0136] Fig. 23 is a schematic diagram showing an example of a process for identifying answer candidates based on attribute relevance using a query extraction filter. Fig. 24 is a schematic diagram showing an example of a process for identifying answer candidates based on attribute relevance using an answer extraction filter. For example, assume that the following utterances (1) to (3) are made. Example utterance (1): "I'd like to speak to Yamada-san from sales, please." Example utterance (2): "I'd like to speak to Kawano-san from development, please." Example utterance (3): "I'd like someone with technical skills who understands XX products."
[0137] At this time, it is assumed that words expressing attributes are extracted from each example utterance as follows: Example utterance (1) "Yamada" (from the extraction filter for inquiries), "Sales" (from the extraction filter for answers) Example utterance (2): "Kawano" (from the inquiry extraction filter), "development" (from the answer extraction filter) Example utterance (3): "XX product" (from the answer extraction filter), "technology" (from the answer extraction filter)
[0138] In the case of utterance example (1), "Yamada" matches the words contained in the extraction filter for inquiries, "sales" matches the words contained in the extraction filter for answers, and answers #2 and #3 are identified from "Yamada," while answers #3 and #4 are identified from "sales." That is, in the case of utterance example (1), answer #2 (Yamada Taro) is identified from the logical product of the results of the first and second identification processes, and is set as the final answer.
[0139] In the case of utterance example (2), "Kawano" matches the words contained in the extraction filter for inquiries, and "development" matches the words contained in the extraction filter for answers, so the answer #1 is identified from both "Kawano" and "development." That is, in the case of utterance example (2), the answer #1 (Kawano Saburo) is identified from the results of the first identification process or the second identification process, and is determined to be the final answer.
[0140] In the case of utterance example (3), the attributes do not match the words contained in the inquiry extraction filter, but "XX product" and "technology" match the words contained in the answer extraction filter, and answers #1 and #3 are identified from "XX product," while answer #1 is identified from "technology." That is, in the case of utterance example (3), answer #1 (Kono Saburo) is identified from the result of the second identification process and becomes the final answer.
[0141] [Operation] Next, the operation of the information processing system 1 will be described. FIG. 25 is a flowchart showing the flow of the automatic response process executed by the information processing system 1. The automatic response process is started in response to an operation being performed in the server 20 to instruct execution of the automatic response process. The automatic response processing in this embodiment differs from the automatic response processing in the first embodiment shown in FIG. 10A in that the processing of step S41-1 is changed to step S41-1A, the processing of step S41-2 is changed to step S41-2A, and the processing of steps S5 to S9 is changed to steps S105 to S107.
[0142] That is, in step S4, the voice recognition processing unit 153 of the server 20 executes voice recognition processes (S41-1A to S43-1 and S41-2A to S43-2) in parallel on the pre-processed voice data using a plurality of voice recognition engines. Specifically, in step S41-1A, the word extraction speech recognition unit 501A processes the speech data using a speech recognition engine for performing speech recognition processing for word extraction (here, this is assumed to be speech recognition processing using a rule grammar or speech recognition processing using a DNN), extracts specific words included in the speech data, and converts them into text data. Note that the speech recognition processing in step S41-1A is a speech recognition processing for extracting words included in an expected inquiry, and the speech recognition processing is performed by referring to a dictionary for word extraction in which words included in the expected inquiry are registered in advance.
[0143] In step S41-2A, the word extraction speech recognition unit 511 processes the speech data using a speech recognition engine for performing speech recognition processing for word extraction (here, speech recognition processing using a rule grammar or DNN), extracts specific words included in the speech data, and converts them into text data. Note that the speech recognition processing in step S41-2A is a speech recognition processing for extracting words included in answers prepared for anticipated inquiries, and the speech recognition processing is performed by referring to a dictionary for word extraction in which words included in answers prepared for anticipated inquiries are registered in advance. After steps S43-1 and S43-2, the process proceeds to step S105.
[0144] In step S105, the narrowing down processing unit 155 executes the first and second specification processes to specify a final answer to the uttered inquiry. That is, the narrowing down processing unit 155 judges whether or not the voice recognition result of the word extraction acquired by the voice recognition processing unit 153-1 (i.e., the words included in the expected inquiry) matches the words included in the extraction filter for the inquiry, and if they match, narrows down the answers prepared in advance based on the matching words included in the extraction filter for the inquiry. In addition, the narrowing down processing unit 155 judges whether or not the voice recognition result of the word extraction acquired by the voice recognition processing unit 153-2 (i.e., the words included in the answer prepared for the expected inquiry) matches the words included in the extraction filter for the answer, and if they match, narrows down the answers prepared in advance based on the matching words included in the extraction filter for the answer. Then, the narrowing down processing unit 155 specifies a final answer to the uttered inquiry based on the narrowing down results of the first and second specification processes.
[0145] In step S106, the integration processing unit 156 transmits the identified final answer as voice or text data to the terminal device 10. The transmitted answer data is received by the response receiving unit 53 of the terminal device 10, and is output by the response output unit 54 as voice or image display. Note that the response output in step S106 may be a response that prompts speech to uniquely identify multiple answer candidates, or a response that outputs multiple answer candidates, in addition to a case where a uniquely identified answer is responded to.
[0146] In step S107, the integrated processing unit 156 determines whether or not a termination condition for the automatic response process is met. The termination condition for the automatic response process can be defined as, for example, a unique response to an uttered inquiry being identified and a response being output, or an operation for terminating the inquiry being performed by the user. If the end condition for the inquiry process is not met, the result of the determination in step S107 is NO, and the process proceeds to step S1. On the other hand, if the end condition for the automatic response process is met, the result of the determination in step S107 is YES, and the automatic response process ends.
[0147] As described above, in the information processing system 1 of this embodiment, a first identification process is executed in parallel to identify answer candidates based on attribute relevance using an extraction filter for a query generated from attributes of an anticipated query, and a second identification process is executed in parallel to identify answer candidates based on attribute relevance using an extraction filter for an answer generated from attributes of answers prepared for the anticipated query, and the answer identified in the first identification process or the second identification process is output as the final answer. Therefore, it is possible to identify an answer to a query from the content of the anticipated query and the attributes of the answers prepared for the anticipated query, without performing language processing to identify answer candidates. Therefore, when an automatic response to a speech is made, it is possible to specify more appropriate response content while shortening the processing time.
[0148] [Variation 1] In each of the above-described embodiments, a case has been described in which a plurality of tables are generated as search data, but the present invention is not limited to this. In other words, the format of the search data is not particularly limited, and as long as the answer can be identified by tracing the relationships between data (words representing attributes, answer numbers, etc.), it can be composed of a single table or a group of data whose relationships are defined by pointers, etc.
[0149] [Variation 2] In the second embodiment, the narrowing-down process 2 has been described as specifying answer candidates based on attribute relevance, based on the latest utterance and the previous utterance, but is not limited to this. That is, the narrowing-down process 2 can specify answer candidates based on the attribute relevance, based on the latest utterance and any number of past utterances preceding the latest utterance. This makes it possible to appropriately set the number of past utterances reflected in the narrowing-down process 2 according to statistical data or the purpose to which the information processing system 1 is applied. In addition, as narrowing-down process 2, multiple processes (i.e., multiple-layer narrowing-down process 2) can be executed in parallel to identify answer candidates based on attribute relevance, based on the most recent utterance and a predetermined number of different past utterances preceding the most recent utterance. This makes it possible to continue the narrowing down process by utilizing the narrowing down results (narrowing down table) based on the most recent specified number of utterances, even if the direction of the user's inquiry changes or if the user speaks words that do not conform to the guidance from the system. Therefore, it is possible to narrow down the answers by accurately reflecting the user's intention, so that an appropriate answer to the inquiry can be identified quickly in accordance with the user's preferences.
[0150] [Variation 3] In the first and second embodiments, the voice recognition processing unit 153 includes the first voice recognition unit 153-1 to the n-th voice recognition unit 153-n, and a case where a plurality of voice recognition processes are executed in parallel has been described as an example, but is not limited thereto. For example, the voice recognition processing unit 153 may output a result of a voice recognition process by one voice recognition engine (for example, a voice recognition engine that performs general-purpose dictation, etc.), and may execute in parallel a process of identifying answer candidates by language processing and a process of identifying answer candidates based on attribute relevance for this voice recognition result. For example, the narrowing-down processes 1 to 3 of the second embodiment and a process of identifying answer candidates by language processing may be executed in parallel for one voice recognition result. In addition to identifying candidate answers based on language processing and candidate answers based on attribute relevance for one voice recognition result, it is also possible to identify the content of the dialogue (message) that induces the speaking of attributes that are effective in identifying an answer. At this time, in response to an inquiry utterance by a user, a dialogue may be generated using AI (Artificial Intelligence) to induce an answer or an utterance of an attribute that is effective in identifying an answer. In this case, it is possible to obtain more useful information than the processing result obtained by a single voice recognition process while suppressing an increase in the processing load. The types of voice recognition processing that can be used at this time include general-purpose dictation, dictation for a specific field, and voice recognition through word extraction.
[0151] [Variation 4] In the second embodiment, an example has been described in which a speech recognition process is performed on a user's speech to extract words using an extraction filter, and then, based on the extracted words, narrowing down answer candidates based on attribute relevance through narrowing down processes 1 to 3; however, this is not limited to this. That is, in addition to a mode in which the user speaks including words for narrowing down answers and the words are input by voice recognition, a mode in which the words are input by operating the screen can also be used. For example, words for an inquiry to be entered into narrowing-down process 1 can be entered by operating the screen, or words for further narrowing down the answer candidates narrowed down by narrowing-down process 1 or narrowing-down process 2 can be entered by operating the screen. A form in which words are input by operating the screen can be a form in which words (words representing attributes) related to answer candidates are scrolled (moved and displayed) in a window on the display (output unit 816) of the terminal device 10, and the user selects a word by clicking or tapping with the mouse, etc. Also, other forms in which words are input by operating the screen can be a form in which words (words representing attributes) related to answer candidates are listed in a window on the display (output unit 816) of the terminal device 10 using a pull-down menu or the like, and the user selects a word by clicking or tapping with the mouse, or a form in which words are listed in a table format, and the user selects a word by checking a check box attached to each word.
[0152] Note that words stored in each table included in the connector tables can be displayed as words to be selected in the narrowing-down process 1. Also, words stored in each table included in the narrowing-down tables 1 or 2 (i.e., words after narrowing down by the narrowing-down process) can be displayed as words to be selected in the narrowing-down process 2 or 3. When inputting words by operating the screen, the user can select effective words for identifying the answer using candidate words displayed on the screen as hints. It is also possible to display words (words representing attributes) related to answer candidates on the screen in any of the above formats, and for the user to select a word by speaking any of the words. Furthermore, in addition to inputting words by operating the screen, it is also possible to input words by operating a keyboard or the like. In this case, in response to the user inputting any text (such as a word or a sentence), the words contained in the input text can be extracted, thereby narrowing down answer candidates based on attribute relevance.
[0153] [Variation 5] In the above embodiment and modified examples, the case where an inquiry is received by voice has been described, but the present invention is not limited to this. That is, it is also possible to accept inquiries by text data, such as inquiries by chat. Therefore, in the above-described embodiment and modified examples, the configuration for performing voice recognition processing on a voice inquiry can be appropriately replaced with a configuration for acquiring text data representing the contents of the inquiry.
[0154] The information processing system 1 configured as above includes the connector DB 174, the voice recognition processing unit 153, the narrowing-down processing unit 155, and the integration processing unit 156. The connector DB 174 stores first attribute information regarding the anticipated inquiries. The connector DB 174 stores second attribute information regarding responses to anticipated inquiries. The voice recognition processor 153 acquires the contents of the inquiry. The narrowing down processing unit 155 and the integration processing unit 156 identify a response (answer or dialogue message) including an answer to the inquiry based on attribute information possessed by the voice recognition result by the voice recognition processing, the first attribute information, and the second attribute information. This makes it possible to identify a response to an inquiry from the content of the anticipated inquiry and the attributes of the response prepared for the anticipated inquiry. Therefore, when an automatic response to an inquiry is made, it is possible to shorten the processing time and specify more appropriate response content.
[0155] The voice recognition processing unit 153 acquires a voice recognition result obtained by subjecting an utterance for inquiry to voice recognition processing. This makes it possible to shorten the processing time and specify more appropriate response content when a voice inquiry is made.
[0156] The narrowing-down processing unit 155 identifies a response including an answer to the inquiry based on attribute information contained in the voice recognition result by the voice recognition processing, the first attribute information, the second attribute information, and expanded attribute information representing attributes expanded from the first attribute information and the second attribute information. This makes it possible to easily identify an answer that matches the spoken inquiry even when unexpected expressions are used, such as when there is variation in expression or when words with similar meanings are used.
[0157] The information processing system 1 also includes a voice recognition processing unit 153 , a language processing unit 154 , a narrowing-down processing unit 155 , and an integration processing unit 156 . The voice recognition processing unit 153 acquires a voice recognition result obtained by subjecting an utterance for inquiry to voice recognition processing. The language processing unit 154 identifies answer candidates that match the inquiry from the meaning expressed by the voice recognition result by the voice recognition processing unit 153 through language processing. The narrowing-down processing unit 155 extracts words contained in the query from the voice recognition result by the voice recognition processing unit 153, and identifies candidate answers that match the query based on the relevance between attribute information based on the words contained in the query and attribute information based on the answers to the query. The integration processing unit 156 identifies a response including an answer to the inquiry based on the answer candidates identified by the language processing unit 154 and the answer candidates identified by the narrowing down processing unit 155. This makes it possible to identify an answer to a query using not only an identification method based on language processing, but also an identification method based on the consistency of words expressing attributes. Therefore, when an automatic response to a speech is made, it is possible to specify more appropriate response content while shortening the processing time.
[0158] The narrowing-down processing unit 155 identifies responses including an answer to the inquiry, based on attribute information based on the answer to the inquiry and expanded attribute information representing attributes expanded from the attribute information based on the answer to the inquiry. This makes it possible to easily identify an answer that matches the spoken inquiry even when unexpected expressions are used, such as when there is variation in expression or when words with similar meanings are used.
[0159] When the accuracy of the answer candidate acquired by the language processing unit 154 is equal to or greater than a set threshold, the integration processing unit 156 determines the answer candidate acquired by the language processing unit 154 as the answer, and when the accuracy of the answer candidate acquired by the language processing unit 154 is less than a set threshold, the integration processing unit 156 determines the answer candidate identified by the narrowing down processing unit 155 as the answer. This makes it possible, when a query is spoken, to quickly obtain a more accurate speech recognition result and identify an appropriate answer.
[0160] The information processing system 1 also includes a voice recognition processing unit 153 , a narrowing-down processing unit 155 , and an integration processing unit 156 . The narrowing-down processing unit 155 generates search data consisting of one or more attributes associated with the answer to the expected inquiry based on first attribute information related to the expected inquiry and second attribute information related to the answer to the expected inquiry. The voice recognition processor 153 acquires the contents of the inquiry. The narrowing down processing unit 155 and the integration processing unit 156 identify a response including an answer to the content of the inquiry based on the attribute information of the content of the inquiry and the search data. This allows for rapid identification of an answer when an inquiry is made using the search data.
[0161] The voice recognition processing unit 153 acquires a voice recognition result obtained by subjecting an utterance for inquiry to voice recognition processing. This makes it possible to quickly identify an answer when a voice inquiry is made using the search data.
[0162] The search data is prepared before the content of the inquiry is acquired, and when the content of the inquiry is acquired, the generated search data is referenced to identify an answer to the content of the inquiry. As a result, search data is prepared before a query is made, making it possible to quickly identify an answer when a query is made.
[0163] The search data includes response identifying information that represents an attribute that can uniquely identify a response, and response group identifying information that represents an attribute that can identify a plurality of answer candidates. This allows the process of identifying an appropriate answer to be performed depending on whether the words contained in the query utterance represent attributes that can uniquely identify an answer or represent attributes that can identify multiple answer candidates.
[0164] The search data includes expanded attribute information that represents attributes expanded from attributes included in the response specifying information and the response group specifying information. This makes it possible to easily identify an answer that matches the spoken inquiry even when unexpected expressions are used, such as when there is variation in expression or when words with similar meanings are used.
[0165] When the content of an inquiry acquired by the voice recognition processing unit 153 identifies multiple answers to the inquiry, the narrowing-down processing unit 155 narrows down one or more attributes associated with the answers to the anticipated inquiry contained in the search data to an attribute that uniquely identifies the answer to the content of the inquiry, or an attribute that identifies fewer answers to the content of the inquiry. The narrowing-down processing unit 155 executes a dialogue to induce the content of an additional inquiry to identify an answer to the content of the inquiry as a response based on the narrowed-down attributes. This makes it possible to accept further inquiries and identify appropriate answers even if the user does not make an appropriate inquiry.
[0166] The narrowing down processing unit 155 executes in parallel a first narrowing down process which targets the entire original search data to identify an answer to the content of the most recent inquiry, and a second narrowing down process which targets search data whose attributes have been narrowed down from the original search data to identify an answer based on the content of a predetermined number of past inquiries. This can increase the likelihood that a suitable answer will be identified as an answer candidate based on attribute relevance.
[0167] The narrowing-down processing unit 155 executes a third narrowing-down processing in parallel with the first narrowing-down processing and the second narrowing-down processing, which identifies an answer based on the content of a predetermined number of past inquiries different from the second narrowing-down processing. This makes it possible to continue the narrowing down process by utilizing the narrowing down results (narrowing down table) from the most recent specified number of inquiries, even if the direction of the user's inquiry changes or if the user makes an inquiry that does not conform to the guidance from the system. Therefore, it is possible to narrow down the answers by accurately reflecting the user's intention, so that an appropriate answer to the inquiry can be identified quickly in accordance with the user's preferences.
[0168] The narrowing-down processing unit 155 displays on a screen words representing attributes contained in the original search data or words representing attributes narrowed down from the original search data, and narrows down answers to the inquiry content by selecting a word displayed on the screen. This allows the user to select effective words for identifying the answer using the candidate words displayed on the screen as a hint.
[0169] The information processing system 1 also includes a voice recognition processing unit 153 and a narrowing-down processing unit 155. The voice recognition processing unit 153 acquires a voice recognition result obtained by subjecting an utterance for inquiry to voice recognition processing. The narrowing-down processing unit 155 filters attribute information contained in the speech recognition result by the speech recognition processing unit 153 using a filter including, as elements, first attribute information related to an expected inquiry, second attribute information related to a response to the expected inquiry, and expanded attribute information related to the first attribute information and the second attribute information. The narrowing-down processing unit 155 identifies responses including answers to the query utterances based on the filter processing results. This makes it possible to quickly extract words expressing attributes from a query utterance and identify answer candidates based on the relevance of attributes.
[0170] The narrowing-down processing unit 155 identifies first attribute information or second attribute information related to a word extracted from the inquiry utterance, and identifies an answer to the expected inquiry associated with the first attribute information or the second attribute information as an answer to the inquiry utterance. This makes it possible to easily identify answers related to words included in the query utterance.
[0171] The present invention is not limited to the above-described embodiment, and modifications and improvements within the scope of the present invention that can achieve the object of the present invention are included in the present invention. For example, in the above embodiment, the information processing system 1 is configured as a system including a plurality of information processing devices, but the present invention is not limited to this. That is, the present invention may be realized by providing the functions of the information processing system 1 to a single information processing device.
[0172] Furthermore, the functions of the server 20 may be distributed among a plurality of servers, some of the functions of the server may be implemented in the terminal device 10, or some of the functions of the terminal device 10 may be implemented in the server. For example, in each of the above-described embodiments, the voice recognition processing is executed in the server 20, but the voice recognition processing may be executed in the terminal device 10, or the voice recognition results executed in another system, etc. may be acquired (received, etc.) and used for processing. In addition, in each of the above-described embodiments, the search data can be updated sequentially in response to updates to the response content table or updates (addition, modification, deletion, etc.) to words expressing attributes based on the operation results.
[0173] Furthermore, the present invention can be implemented by appropriately combining the configurations described in the above-mentioned embodiments and modifications. The above-described series of processes can be executed by hardware or software. In other words, the functional configurations of Figures 3, 4, 9, 16, and 17 are merely examples and are not particularly limited. In other words, it is sufficient for the information processing system 1 to have a function capable of executing the above-mentioned series of processes as a whole, and the type of functional block used to realize this function is not particularly limited to the examples of Figures 3, 4, 9, 16, and 17. Furthermore, one functional block may be configured as a single piece of hardware, a single piece of software, or a combination of both.
[0174] When the series of processes is executed by software, the program constituting the software is installed into a computer or the like from a network or a recording medium. The computer may be a computer built into dedicated hardware, or may be a computer capable of executing various functions by installing various programs, such as a general-purpose personal computer.
[0175] The storage medium that stores the program is composed of a removable medium distributed separately from the device body, or a storage medium that is pre-installed in the device body. The removable medium is composed of, for example, a magnetic disk, an optical disk, a magneto-optical disk, or a flash memory. The optical disk is composed of, for example, a CD-ROM (Compact Disk-Read Only Memory), a DVD (Digital Versatile Disk), a Blu-ray Disc (registered trademark), or the like. The magneto-optical disk is composed of, for example, an MD (Mini-Disk), or the like. The flash memory is composed of, for example, a USB (Universal Serial Bus) memory or an SD card. The storage medium pre-installed in the device body is composed of, for example, a ROM in which the program is stored, a hard disk, or a flash memory, or the like.
[0176] In this specification, the steps of describing a program to be recorded on a recording medium include not only processes that are performed chronologically according to the order, but also processes that are not necessarily performed chronologically but are executed in parallel or individually. In addition, in this specification, the term "system" refers to an overall device that is composed of a plurality of devices, a plurality of means, etc. [Explanation of symbols]
[0177] 1 Information processing system, 10 Terminal device, 20 Server, 30 Network, 800 Information processing device, 811 CPU, 812 ROM, 813 RAM, 814 Bus, 815 Input unit, 815a Operation input unit, 815b Voice input unit, 816 Output unit, 817 Storage unit, 818 Communication unit, 819 Drive, 820 Imaging unit, 831 Removable media, 51 Speech reception unit, 52 Speech data transmission unit, 53 Response reception unit, 54 Response output unit, 151 Speech data reception unit, 152 Preprocessing unit, 153 Speech recognition processing unit, 153-1 First speech recognition unit, 153-2 Second speech recognition unit, 154 Language processing unit, 155 Narrowing processing unit, 156 Integration processing unit, 171 Speech recognition dictionary database (speech recognition dictionary DB), 172 Word dictionary database (word dictionary DB), 173 Response content database (response content DB), 174 connector database (connector DB), 501 dictation speech recognition unit, 502 first recognition result determination unit, 503 first recognition result output unit, 511 word extraction speech recognition unit, 512 second recognition result determination unit, 513 second recognition result output unit
Claims
1. An information processing system including one or more information processing devices, a search data generating means for generating search data composed of one or more attributes associated with the answer to the anticipated inquiry based on first attribute information related to the anticipated inquiry and second attribute information related to the answer to the anticipated inquiry; An inquiry content acquisition means for acquiring the content of an inquiry; a response identifying means for identifying a response including an answer to the content of the inquiry based on attribute information of the content of the inquiry and the search data; Equipped with the attribute information of the content of the inquiry, the first attribute information, and the second attribute information are expressed by words; the search data includes expanded attribute information including synonyms, which are words having the same meaning and words expressing a similar concept, for the words expressing the first attribute information and the second attribute information; The information processing system is characterized in that the response identification means identifies a response including an answer to the content of the inquiry by searching the search data for words representing attribute information contained in the content of the inquiry.
2. 2. The information processing system according to claim 1, wherein the inquiry content acquisition means acquires a speech recognition result obtained by subjecting an utterance for making an inquiry to speech recognition processing.
3. An information processing system as described in claim 1 or 2, characterized in that the search data is prepared before the content of the inquiry is acquired, and when the content of the inquiry is acquired, an answer to the content of the inquiry is identified by referring to the generated search data.
4. 4. The information processing system according to claim 1, wherein the search data includes response identification information representing attributes that can uniquely identify the answer, and response group identification information representing attributes that can identify multiple answer candidates.
5. 5. The information processing system according to claim 4, wherein the search data includes the extended attribute information representing an attribute extended from the attribute included in the response specifying information and the response group specifying information.
6. When a plurality of answers to the inquiry are identified by the content of the inquiry acquired by the inquiry content acquisition means, the search data generation means narrows down one or more attributes associated with the answers to the assumed inquiry included in the search data to an attribute that uniquely identifies the answer to the content of the inquiry, or an attribute that identifies fewer answers to the content of the inquiry; The information processing system according to any one of claims 1 to 5, characterized in that the response identification means executes, as the response, a dialogue to guide the content of an additional inquiry to identify an answer to the content of the inquiry based on the attributes narrowed down by the search data generation means.
7. The response identification means a first narrowing-down process for identifying an answer to the latest inquiry content from the entire original search data; a second narrowing process for identifying an answer based on the content of the inquiry made a predetermined number of times in the past, using the search data whose attributes have been narrowed down from the original search data as a target; 7. The information processing system according to claim 1, wherein the above steps are executed in parallel.
8. The information processing system according to claim 7, characterized in that the response identification means executes a third narrowing-down process in parallel with the first narrowing-down process and the second narrowing-down process, in which a response is identified based on the content of a predetermined number of past inquiries different from the second narrowing-down process.
9. The information processing system according to any one of claims 1 to 8, characterized in that the response identification means displays on a screen words representing attributes contained in the original search data or words representing attributes narrowed down from the original search data, and narrows down answers to the content of the inquiry by selecting a word displayed on the screen.
10. An information processing system including one or more information processing devices, A speech recognition means for acquiring a speech recognition result obtained by subjecting a speech for a query to speech recognition processing; a filter processing means for filtering attribute information included in a speech recognition result by said speech recognition means using a filter including, as elements, first attribute information related to an expected inquiry, second attribute information related to a response to said expected inquiry, and expanded attribute information related to said first attribute information and said second attribute information; a response identifying means for identifying a response including a response to the utterance for inquiry based on a filtering process result by the filtering means; Equipped with the attribute information contained in the speech recognition result of the query utterance, the first attribute information, the second attribute information, and the expanded attribute information are expressed by words; the filter includes synonyms, which are words having the same meaning and words expressing a similar concept, for the words expressing the first attribute information and the second attribute information; The information processing system is characterized in that the response identification means identifies a response including an answer to the content of the inquiry by a process of searching for words representing attribute information of the speech recognition result by the speech recognition means detected by the filter processing means.
11. The information processing system according to claim 10, characterized in that the response identification means identifies the first attribute information or the second attribute information related to a word expressing the attribute information extracted from the utterance for the inquiry by the filter processing means, and identifies a response to the expected inquiry associated with the first attribute information or the second attribute information as a response to the utterance for the inquiry.
12. An information processing method executed in an information processing system including one or more information processing devices, a search data generating step of generating search data composed of one or more attributes associated with the answer to the anticipated inquiry based on first attribute information related to the anticipated inquiry and second attribute information related to the answer to the anticipated inquiry; An inquiry content acquisition step of acquiring the content of the inquiry; a response identifying step of identifying a response including an answer to the content of the inquiry based on attribute information of the content of the inquiry and the search data; Including, the attribute information of the content of the inquiry, the first attribute information, and the second attribute information are expressed by words; the search data includes expanded attribute information including synonyms, which are words having the same meaning and words expressing a similar concept, for the words expressing the first attribute information and the second attribute information; The information processing method is characterized in that in the response identification step, a response including an answer to the content of the inquiry is identified by searching the search data for words representing attribute information contained in the content of the inquiry.
13. An information processing method executed in an information processing system including one or more information processing devices, a speech recognition step of obtaining a speech recognition result obtained by subjecting a speech for a query to speech recognition processing; a filtering step of filtering attribute information of the speech recognition result in the speech recognition step using a filter including, as elements, first attribute information related to an expected inquiry, second attribute information related to a response to the expected inquiry, and expanded attribute information related to the first attribute information and the second attribute information; a response identifying step of identifying a response including an answer to the utterance for the query based on a filtering result in the filtering step; Including, the attribute information contained in the speech recognition result of the query utterance, the first attribute information, the second attribute information, and the expanded attribute information are expressed by words; the filter includes synonyms, which are words having the same meaning and words expressing a similar concept, for the words expressing the first attribute information and the second attribute information; an information processing method, characterized in that in the response identifying step, a response including an answer to the content of the inquiry is identified by a process of searching for words expressing attribute information of the speech recognition result in the speech recognition step detected in the filtering process step.
14. On the computer, a search data generation function that generates search data composed of one or more attributes associated with the answer to the anticipated inquiry based on first attribute information related to the anticipated inquiry and second attribute information related to the answer to the anticipated inquiry; An inquiry content acquisition function for acquiring the content of an inquiry; a response identification function that identifies a response including an answer to the content of the inquiry based on attribute information of the content of the inquiry and the search data; Realize this, the attribute information of the content of the inquiry, the first attribute information, and the second attribute information are expressed by words; the search data includes expanded attribute information including synonyms, which are words having the same meaning and words expressing a similar concept, for the words expressing the first attribute information and the second attribute information; The response identification function is a program characterized by identifying a response containing an answer to the content of the inquiry by searching the search data for words representing attribute information contained in the content of the inquiry.
15. On the computer, A speech recognition function for acquiring a speech recognition result obtained by subjecting a speech for a query to speech recognition processing; a filter processing function for filtering attribute information of the speech recognition result by the speech recognition function using a filter including, as elements, first attribute information related to an expected inquiry, second attribute information related to a response to the expected inquiry, and expanded attribute information related to the first attribute information and the second attribute information; a response identification function that identifies a response including an answer to the utterance for the query based on a filtering result by the filtering function; Realize this, the attribute information contained in the speech recognition result of the query utterance, the first attribute information, the second attribute information, and the expanded attribute information are expressed by words; the filter includes synonyms, which are words having the same meaning and words expressing a similar concept, for the words expressing the first attribute information and the second attribute information; The response identification function is a program characterized by identifying a response including an answer to the content of the inquiry by a process of searching for words that represent attribute information of the voice recognition result by the voice recognition function detected by the filter processing function.
Citation Information
Patent Citations
Response generation program, response generation method and response generation apparatus
JP2006031467A
Information providing system, information providing method, program and data structure
JP2016099968A
Interactive business support system and interactive business support program
JP2019003319A
Information search system and method
JP2019139746A
Interactive business assistance system
JP2019207648A
