Analysis support server and analysis support method

Abstract

Analyze time-series data related to devices using a simple method. [Solution] The analysis support includes an acquisition unit that acquires time-series data including data at multiple points in time measured by a sensor device specified by the user; an input unit that submits an analysis request to an analysis server, including the time-series data and questions regarding the time-series data; and a presentation unit that presents the user with the answers from the analysis server to the questions.

Description

[Technical Field]

[0001] The present invention relates to an analysis support server and an analysis support method. [Background Art]

[0002] In recent years, chatbots using large-scale language models have been put into practical use. Chatbots can also be used for data analysis. Patent Document 1 proposes a technique for analyzing stock price data, which is time-series data, using a language model. [Prior Art Literature] [Patent Literature]

[0003] [Patent Document 1] Japanese Unexamined Patent Application Publication No. 2019-46158 [Summary of the Invention] [Problem to be Solved by the Invention]

[0004] It is conceivable that a user analyzes time-series data by specifying a specific device. Some aspects of the present invention aim to provide a technique for analyzing time-series data related to a device by a simple method. [Means for Solving the Problem]

[0005] According to some embodiments, there is provided an analysis support server comprising: first acquisition means for acquiring time-series data related to a device specified by a user; second acquisition means for acquiring a question related to the time-series data from the user; input means for inputting an analysis request including the time-series data and the question to an analysis server; and presentation means for presenting an answer to the question to the user based on an analysis result obtained by the analysis server. [Effect of the Invention]

[0006] According to some embodiments, time-series data related to a device can be analyzed in a simple manner. [Brief explanation of the drawing]

[0007] [Figure 1] A block diagram illustrating an example configuration of an analysis system in some embodiments. [Figure 2] A block diagram illustrating an example of the hardware configuration of components of an analysis system in some embodiments. [Figure 3] A flowchart illustrating an example of the operation of a management server in one of the embodiments. [Figure 4] A flowchart illustrating an example of the operation of an analysis support server in some embodiments. [Figure 5] A sequence diagram illustrating an example of the operation of an analysis support server in one of the embodiments. [Modes for carrying out the invention]

[0008] The embodiments will be described in detail below with reference to the attached drawings. Note that the following embodiments do not limit the invention as defined in the claims, and not all combinations of features described in the embodiments are essential to the invention. Two or more of the features described in the embodiments may be combined in any way. Furthermore, identical or similar configurations will be given the same reference numeral, and redundant descriptions will be omitted.

[0009] Referring to Figure 1, an example configuration of an analysis system 100 according to one embodiment will be described. The analysis system 100 may include a management server 101, an analysis support server 104, and an analysis server 106.

[0010] The management server 101 manages one or more sensor devices 102. Since the management server 101 typically manages multiple sensor devices 102, multiple sensor devices 102 are shown in Figure 1. For example, the management server 101 receives sensor data from each of the one or more sensor devices 102 and stores the time-series data 111 composed of that sensor data in the storage 103. A sensor device 102 may be any device having a sensor. A sensor device 102 may be capable of transmitting sensor data to the management server 101 via a network. The network between the sensor device 102 and the management server 101 may be a cellular network, a local area network, a wide area network (e.g., the Internet), or any combination thereof. A sensor device 102 may also be a communication device, and in particular, an IoT (Internet of Things) device. A communication device may be any device that can connect to a network. An IoT device may be any device that can connect to the Internet. The embodiments described below are applicable not only to sensor devices 102 (i.e., devices having sensors) but also to devices that do not have sensors. Devices without sensors may periodically transmit numerical data acquired through calculations to the management server 101. Devices without sensors may also be communication devices, particularly IoT devices.

[0011] The analysis server 106 provides a service that answers the input questions. In particular, the analysis server 106 may answer questions by analyzing the input data. The analysis server 106 may generate answers using, for example, a large-scale language model trained by machine learning. The analysis server 106 may provide a chatbot such as OpenAI's ChatGPT. The chatbot may answer questions asked in natural language in natural language.

[0012] The analysis support server 104 provides a service to support the analysis of time-series data 111 using the analysis server 106. Hereinafter, such a service will be referred to as the analysis support service. For example, the analysis support server 104 may provide the analysis support service to the user through the client terminal 105. The analysis support server 104 can communicate with the management server 101, the client terminal 105, the analysis server 106, and the storage 103. The network between these devices can be any network.

[0013] Storage 103 stores data used by the analysis system 100. Storage 103 may be, for example, a database. Storage 103 may store time-series data 111 acquired from one or more sensor devices 102, a candidate question list 112, and past cases 113. The candidate question list 112 and past cases 113 will be described later. In Figure 1, the time-series data 111, the candidate question list 112, and past cases 113 are stored in one storage 103. Alternatively, this data may be distributed and stored in multiple storages. At least a portion of the data stored in storage 103 may be stored on one of the servers of the analysis system 100.

[0014] The management server 101, analysis support server 104, and analysis server 106 described above may all be configured using devices within an on-premises environment or using computing resources within a cloud computing environment. The management server 101 and the analysis support server 104 may be configured using separate devices or using the same device.

[0015] Referring to Figure 2(a), an example of the hardware configuration of a computer 200 according to one embodiment will be described. The computer 200 may be used as any of the management server 101, the analysis support server 104, the client terminal 105, or the analysis server 106 described above.

[0016] Computer 200 may have the hardware devices shown in Figure 2(a). The processor 201 controls the overall operation of computer 200. The processor 201 may consist of, for example, a central processing unit (CPU), a graphics processing unit (GPU), or a combination thereof. The processor 201 may be a single processor or a collection of multiple processors connected to each other in a communicative manner.

[0017] Memory 202 stores programs and data used for processing by the computer 200. Memory 202 may be configured, for example, as a combination of random access memory (RAM) and read-only memory (ROM).

[0018] The input device 203 is a device for obtaining instructions from the user of the computer 200. The input device 203 may consist of one or more combinations of, for example, a keyboard, buttons, a touchpad, and a microphone. The display device 204 is a device for visually presenting information to the user of the computer 200. The display device 204 may be a dot-matrix display, such as a liquid crystal display. The computer 200 may have a device in which the input device 203 and the display device 204 are integrated (for example, a touchscreen). The input device 203 and the display device 204 may be located outside the computer. In this case, the computer 200 may have an interface for communicating with the external input device 203 and display device 204.

[0019] The communication device 205 is a device for communicating with a device external to the computer 200. When the computer 200 performs wired communication, the communication device 205 may be a network interface card (NIC) having a connector for connecting a cable. When the computer 200 performs wireless communication, the communication device 205 may be a wireless communication module including an antenna and a baseband processing circuit.

[0020] The secondary storage device 206 is a device for non-volatilely storing programs and data used for processing by the computer 200. The secondary storage device 206 is configured by, for example, a hard disk drive (HDD) or a solid state drive (SSD).

[0021] In the following description, a component (e.g., processor 201) of the computer 200 that functions as a specific device (e.g., management server 101) is referred to as a component of the specific device (e.g., processor 201 of the management server 101).

[0022] With reference to FIG. 2(b), an example of the hardware configuration of the sensor device 102 according to some embodiments will be described. The sensor device 102 may include the hardware device shown in FIG. 2(b). The processor 211 to communication device 215 may have the same functions as the processor 201 to communication device 205. The sensor device 102 may have a simpler configuration compared to a general computer 200 (e.g., a smartphone or a personal computer). For example, the input device 213 may be a hardware button. The display device 214 may be an indicator. The sensor device 102 does not need to include at least one of the input device 213 and the display device 214.

[0023] Sensor 216 is a device for measuring specific data. Sensor 216 may be any type of sensor, such as a temperature sensor, humidity sensor, acceleration sensor, illuminance sensor, vibration sensor, positioning sensor, pressure sensor, acoustic sensor, or image sensor. Sensor device 102 may include multiple types of sensors 216. For example, if sensor device 102 is a thermometer / hygrometer, sensor device 102 may include a temperature sensor and a humidity sensor as sensors 216. Sensor device 102 may be powered by a battery (not shown) or by an external power source.

[0024] Referring to Figure 3, an example of the operation of the management server 101 will be described. The operation in Figure 3 may be performed by the processor 201 of the management server 101 executing a program read into the memory 202 of the management server 101. Alternatively, some or all of the steps of the operation in Figure 3 may be performed by a dedicated integrated circuit, such as an application-specific integrated circuit (ASIC). The same applies to the operations of the analysis support server 104 and the analysis server 106, which will be described below. The operation in Figure 3 may be started when the administrator of the management server 101 starts the management server 101. In the description of Figure 3, the management server 101 acquires sensor data from the sensor device 102. Alternatively, the management server 101 may acquire data from a device that does not have a sensor.

[0025] In S301, the management server 101 determines whether it has received sensor data from any of the multiple sensor devices 102 under its management. If the management server 101 determines that it has received sensor data (YES in S301), it proceeds to S302; otherwise (NO in S301), it repeats S301. The sensor device 102 may send sensor data to the management server 101 each time it measures data, or it may send sensor data from multiple points in time to the management server 101 all at once.

[0026] In S302, the management server 101 identifies which of the multiple managed sensor devices 102 transmitted the sensor data received in S301. The identified sensor device 102 is referred to as the target device. The management server 101 may also identify the target device by an identifier attached to the sensor data. This identifier may be, for example, an identifier used for communication (e.g., a subscriber identification number (IMSI)), or an identifier uniquely assigned by the management server 101 to each sensor device 102. Alternatively or in addition to the above, the management server 101 may identify the target device based on the source address of the sensor data.

[0027] In S303, the management server 101 updates the time-series data 111 stored in the storage 103. The management server 101 manages the time-series data 111 separately for each of the multiple sensor devices 102 under management. If the time-series data 111 for the target device is not stored in the storage 103, the management server 101 stores the sensor data received in S301 in the storage 103 as the time-series data 111 for the target device. If the time-series data 111 for the target device is stored in the storage 103, the management server 101 adds the sensor data received in S301 to the time-series data 111 for the target device.

[0028] When the management server 101 stores sensor data in the storage 103, it may add a timestamp to the sensor data at each point in time. This timestamp may represent the date and time when the sensor data was received by S301, or it may represent the date and time when the processing in S303 was executed. If the sensor data received by S301 already has a timestamp, the management server 101 may use this timestamp as is, or it may update this timestamp.

[0029] Subsequently, the management server 101 returns processing to S301 and waits for the reception of new sensor data. Through these operations, separate time-series data 111 is stored in the storage 103 for each of the multiple sensor devices 102 under management.

[0030] Referring to Figure 4, an example of the operation of the analysis support server 104 will be described. The operation in Figure 4 may be initiated when the analysis support server 104 receives an instruction from a user to analyze time-series data 111 relating to one or more specific sensor devices 102. The specific sensor devices 102 may be specified by the user, for example, using the identifier of the sensor device 102. The sensor device 102 specified by the user will be referred to as the specified device. The specification of the sensor device 102 may be done using an identifier used for communication (for example, the subscriber identification number (IMSI)), or using an identifier uniquely assigned to each sensor device 102 by the management server 101. The specified device may be one sensor device 102 or multiple sensor devices 102. When one sensor device 102 is specified, the time-series data 111 relating to this one sensor device 102 is analyzed. When multiple sensor devices 102 are specified, the time-series data 111 relating to these multiple sensor devices 102 is analyzed together. The designated device may be a sensor device 102 owned by the user who instructed the analysis, or it may be a sensor device 102 not owned by this user. The time-series data relating to the sensor device 102 not owned by the user who instructed the analysis may be so-called open data.

[0031] The analysis support server 104 may function as a web server that provides a graphical user interface to the user through the client terminal 105. Specifically, the analysis support server 104 may present an operation screen to the user through the client terminal 105 and obtain instructions for this operation screen.

[0032] In S401, the analysis support server 104 retrieves the time-series data 111 of the specified device stored in the storage 103. The analysis support server 104 may read the time-series data 111 of the specified device directly from the storage 103, or it may read it via the management server 101. The analysis support server 104 may or may not present the retrieved time-series data 111 to the user.

[0033] In S402, the analysis support server 104 obtains a question from the user for the analysis server 106. This question may be one selected by the user from one or more candidate questions presented by the analysis support server 104, or it may be a question arbitrarily entered by the user. For example, the question may be a sentence expressed in natural language, such as "Please explain the data." The question may also be an expression of what the user wants to know. The question may be expressed as a declarative sentence or an interrogative sentence.

[0034] Candidate questions may be questions applicable to time-series data 111 of any type of sensor device 102 (for example, "Please describe the data"). Such questions are referred to as general-purpose questions. General-purpose questions may be predetermined by the administrator of the analysis support server 104 and stored in the storage 103 in the candidate question list 112. The type of sensor device 102 may be classified by the type of sensor 216 that the sensor device 102 has.

[0035] Candidate questions may be questions applicable to time-series data 111 of a specific type of sensor device 102. For example, if the sensor device 102 is a thermometer / hygrometer, the question may be, "Is there any specific correlation between temperature changes and humidity changes?" Such questions are referred to as device-specific questions. Device-specific questions may be predetermined by the administrator of the analysis support server 104 and stored in storage 103 as part of the candidate question list 112. Alternatively, or in addition to the above, device-specific questions may be generated by the analysis server 106, as described later.

[0036] In S403, the analysis support server 104 sends an analysis request to the analysis server 106 that includes the time-series data 111 acquired in S401 and the question acquired in S402. This analysis request may be, for example, a sentence like the following. Please answer based on the following CSV data: imsi, timestamp, temp, humi 001011234567890, 1685931995638, 23.4, 56.7 001011234567890, 1685932295638, 23.5, 56.8 (omitted) 001011234567890, 1685942295638, 24.6, 55.5 Please explain the data. The analysis request may include time-series data and the initial question, as well as instructions for performing analysis on the time-series data (in the example above, "Please answer based on the following CSV data"). These instructions may specify the data format of the time-series data (in the example above, CSV (Comma Separated Value) format). The analysis support server 104 may automatically generate instructions based on the data format of the time-series data. Alternatively, these instructions may not specify the data format of the time-series data and may simply be a statement such as "Please answer based on the following data."

[0037] The initial analysis request may be made in a new context. The context may refer to a series of data that the analysis support server 104 has input to the analysis server 106. In other words, making an analysis request in a new context means making a new analysis request that is independent of any data previously input.

[0038] The analysis support server 104 may include all of the time-series data 111 acquired in S401 in the analysis request, or it may include only a portion of it in the analysis request to reduce the amount of data. For example, the analysis support server 104 may include only a specific number or a specific amount of data from the time-series data 111 acquired in S401 in the analysis request. Alternatively or in addition to this, the analysis support server 104 may include only a portion of the time-series data 111 acquired in S401 that is specific to a particular time period in the analysis request. Alternatively or in addition to this, the analysis support server 104 may include only data of a specific item (for example, only timestamp and temperature data) from the time-series data 111 acquired in S401 in the analysis request. The criteria for extracting sensor data may be pre-configured by the administrator of the analysis support server 104, or it may be specified by the user. If the analysis request includes time-series data for multiple sensor devices 102, the time-series data included in the analysis request may be sorted by sensor device, by timestamp, or in any order.

[0039] The analysis server 106 performs the analysis in response to the analysis request submitted by the analysis support server 104 and returns the analysis results to the analysis support server 104. The analysis support server 104 receives these analysis results. In S404, the analysis support server 104 presents the answer to the user based on the analysis results received from the analysis server 106. The analysis support server 104 may present the analysis results to the user as they are, or it may process the analysis results before presenting them to the user. For example, the analysis support server 104 may highlight parts of the analysis results according to predetermined rules (for example, it may highlight keywords such as "important," "necessary," or "noteworthy").

[0040] The analysis support server 104 may store the question submitted to the analysis server 106 and the device information of the specified device as past case 113 in storage 103 before or after the presentation of the answer in S404. The device information may include, for example, the type of the specified device. Past case 113 may be used to generate candidate questions, as will be described later.

[0041] In S405, the analysis support server 104 determines whether the user has requested additional questions. If the analysis support server 104 determines that the user has requested additional questions (YES in S405), it proceeds to S403; otherwise (NO in S405), it terminates the process.

[0042] If instructed to ask additional questions, the analysis support server 104 executes S403 again to submit an analysis request including the additional questions to the analysis server 106. This analysis request may be, for example, a statement like the following: "Please explain why you identified the data that deserves attention." This analysis request may be made in the same context as the previous question. If the analysis server 106 has the function to manage context, the analysis request including the additional question does not have to include the time-series data 111 obtained in S401. On the other hand, if the analysis server 106 does not have the function to manage context, the analysis support server 104 may send a new analysis request to the analysis server 106 that includes the additional question to a previously made analysis request.

[0043] If the user does not provide any further questions, the analysis support server 104 terminates processing. In the example above, the analysis support server 104 stores the content of each analysis request submitted to the analysis server 106 as past case 113. Alternatively, the analysis support server 104 may store the content of the analysis requests collectively as past case 113 after the user has finished asking a series of questions.

[0044] Past Case 113 may include other information in addition to, or instead of, the content entered into the analysis server 106 as described above. For example, Past Case 113 may include text describing past cases using the sensor device 102 or other devices. Such text may have titles such as "Providing energy-saving services by visualizing room temperature data and power usage and remotely controlling air conditioners," "Developing a tire pressure and temperature management service with IoT: A long-established tire manufacturer's challenge to a new business," "Digitizing the reasons for production line stoppages at a long-established factory and improving operations through data analysis," or "Automating safety management of distribution boards in a manufacturing plant with IoT: Enabling detection of distribution board malfunctions through temperature data collection," and may be published as a web page. Such text for Past Case 113 may be written by a person and stored in storage 103. Alternatively, the text for Past Case 113 may be automatically generated by the analysis server 106 or another server.

[0045] Referring to Figure 5, an example of how the analysis support server 104 presents candidate questions to the user will be described. In the method shown in Figure 5, the analysis server 106 creates two instances to manage two independent contexts. One instance manages the context for question generation, and this instance is referred to as the question generation instance 501. The other instance manages the context for data analysis, and this instance is referred to as the analysis instance 502. In the example in Figure 5, the question generation instance 501 and the analysis instance 502 are contained within one analysis server 106. Alternatively, the question generation instance 501 and the analysis instance 502 may be contained within two separate analysis servers 106. If the analysis server 106 does not have the functionality to manage contexts, the analysis support server 104 may perform question generation and data analysis in separate contexts by modifying the content of past requests to be included in new requests.

[0046] In S501, the analysis support server 104 receives an instruction to start analysis support from user 500. As described above with reference to Figure 4, the start instruction includes an identifier to identify the specified device.

[0047] In S502, the analysis support server 104 acquires time-series data 111 from the specified device in the same manner as in S401. In S503, the analysis support server 104 requests the question generation instance 501 to analyze the time-series data 111 acquired in S502. This analysis is performed to generate a base for generating candidate questions. This analysis request may be a statement such as the following: "Please identify the three data series with the largest changes from the following data. Also, what do these data series represent?" --- __time,__iso8601Time,bat,humi,lat,lon,rs,temp,type,x,y,z "2023-06-21 07:04:34","2023-06-21T07:04:34.048+09:00","3","53.7","35.701044","139.673169","4","28.1","0","0","-192","1024" "2023-06-21 07:03:39","2023-06-21T07:03:39.008+09:00","3","53.4","35.701042","139.67317","4","28.1","0","0","-192","1024" "2023-06-21 07:02:34","2023-06-21T07:02:34.053+09:00","3","53.4","35.70104","139.673171","4","27","0","0","-192","1024" "2023-06-21 07:01:33","2023-06-21T07:01:33.962+09:00","3","53.3","35.701039","139.67317","4","28.1","0","0","-192","1024" "2023-06-21 07:00:33","2023-06-21T07:00:33.978+09:00","3","53.7","35.701039","139.67317","4","28.2","0","0","-192","1024" : (Omitted below) ---"

[0048] In S504, the question generation instance 501 performs the analysis. In S505, the question generation instance 501 responds with the analysis results to the analysis support server 104. For example, the following text is responded to. The following three data series show the most significant changes: - humi: The humidity level has changed significantly, from 53.9 to 47.2. - temp: The temperature value is changing significantly from 28.4 to 27. - x: The acceleration value in the x-axis direction changes significantly from 64 to -192. This data appears to be sensor data recording information such as date and time, battery level, humidity, latitude and longitude, temperature, and acceleration.

[0049] In S506, the analysis support server 104, in the same context as S503, requests the question generation instance 501 to suggest examples that can be used as reference for generating candidate questions for the time-series data 111 acquired in S502. This request may be, for example, a statement like the following: "To analyze a data series with the following characteristics, consider what examples would be helpful. For example, if there are large changes in latitude and longitude, it would be good to refer to examples using GPS." --- The following three data series show the most significant changes: - humi: The humidity level has changed significantly, from 53.9 to 47.2. - temp: The temperature value is changing significantly from 28.4 to 27. - x: The acceleration value in the x-axis direction changes significantly from 64 to -192. This data appears to be sensor data recording information such as date and time, battery level, humidity, latitude and longitude, temperature, and acceleration. ---" The analysis support server 104 may generate the text of S506 by adding instructions pre-configured by the administrator to the analysis results received in S505.

[0050] In S507, the question generation instance 501 generates a case suggestion. In S508, the question generation instance 501 responds to the analysis support server 104 with the case suggestion. For example, the following text is responded to. "- humi: When humidity changes rapidly, it can be affected by indoor temperature and outdoor humidity. For example, humidity changes when you change the temperature setting of an air conditioner or after it rains. It would be good to refer to these examples." - temp: When the temperature changes rapidly, it can be affected by indoor and outdoor temperatures. For example, this could be due to temperature changes when changing the air conditioner's temperature setting, or due to temperature differences between day and night. These examples should be considered. - x: If the acceleration changes abruptly, it may be due to the sensor moving. For example, this could be caused by shaking or dropping the sensor. These examples should be considered.

[0051] In S509, the analysis support server 104 identifies the case proposed in S508 from the past case 113. For example, the analysis support server 104 may calculate the similarity between each of the multiple sentences included in the past case 113 and the sentence received in S508, and identify cases where this similarity exceeds a threshold as recommended cases. The similarity of the sentences may be calculated using existing technology.

[0052] In S510, the analysis support server 104, in the same context as S506, requests the question generation instance 501 to generate candidate questions for the time series data 111 acquired in S502. This request may be, for example, a statement like the following. "[Text of identified reference cases]" --- - humi: When humidity changes rapidly, it can be affected by indoor temperature and outdoor humidity. For example, humidity changes when you change the temperature setting of an air conditioner or after it rains. These examples should be helpful. - temp: When the temperature changes rapidly, it can be affected by indoor and outdoor temperatures. For example, this could be due to temperature changes when changing the air conditioner's temperature setting, or due to temperature differences between day and night. These examples should be considered. - x: If the acceleration changes abruptly, it may be due to the sensor moving. For example, this could be caused by shaking or dropping the sensor. You should refer to these examples. --- Focusing on the data above, please prepare five questions to clarify the data. If the reference materials mention the use of similar data, please make your questions related to that. - Please express your questions in bullet points. - I will answer in Japanese. - We will ask questions to gain insights from changes in the data. - I will not ask about the reason why the data changed. - I will not ask about measures taken to address changes in the data. - I will not ask any questions about specific cases. - I will not ask any questions regarding the sensor specifications. - I will not ask any questions about the location where the sensors are installed. - I will not ask questions about data that the sensor cannot acquire. - Please use your vivid imagination to fill in any gaps in the context. Example question: Q: Around what time did the sudden change in data occur? Q: Are there any periodic changes in the data? Q: Are there cases where the temperature changes rapidly or shows extreme values? The [Identified Reference Example Text] included in the above text may contain the example text identified in S509 as is. If multiple texts are identified in S509, the [Identified Reference Example Text] included in the above text may contain multiple texts. If the analysis server 106 has the function of analyzing web pages, the [Identified Reference Example Text] included in the above text may contain the URL of the web page in which the reference example is described.

[0053] In S511, the question generation instance 501 generates candidate questions. In S512, the question generation instance 501 responds to the analysis support server 104 with the candidate questions. For example, the following sentence is responded to. "Q: Are there any characteristic patterns or trends in temperature and humidity values ​​depending on the day of the week or time of day? Specifically, for example, is there a pattern where the temperature is higher on Monday mornings compared to other days of the week or time of day?" Q: Are there any characteristic patterns in the rate of temperature change? For example, are there regular periods or time zones where the rate of temperature change is large, and periods or time zones where it is small? Q: Is there any special correlation between changes in humidity and changes in temperature? Q: Is there any periodicity observed in the time periods when the amount of change in the data is characteristic? In other words, is there a period in which a specific pattern appears regularly? Q: What are the maximum / minimum changes in temperature and humidity? Are there any specific conditions or patterns under which these data changes are observed?

[0054] In S513, the analysis support server 104 presents the candidate questions responded to by the question generation instance 501 to the user 500. In addition to the candidate questions responded to by the question generation instance 501, the analysis support server 104 may also present the user with candidate questions included in the candidate question list 112 stored in the storage 103. If the quality of the candidate questions responded to by the question generation instance 501 is low, or if a response from the question generation instance 501 is not received within a threshold time, the analysis support server 104 may present the user with only the candidate questions included in the candidate question list 112 stored in the storage 103. The analysis support server 104 may request the question generation instance 501 to evaluate the quality of the candidate questions responded to by the question generation instance 501. The analysis support server 104 may present the candidate questions included in the candidate question list 112 stored in the storage 103 and the candidate questions responded to by the question generation instance 501 in a distinguishable manner.

[0055] In S514, the analysis support server 104 obtains a question from user 500 in the same manner as in S402. In S515, the analysis support server 104 requests an analysis from analysis instance 502 in the same manner as in S403. This request is made in a new context. This request is also made in a context different from the context used to generate candidate questions in S503-S512 as described above. In S516, the analysis server 106 performs the analysis. In S517, the analysis server 106 responds with the analysis results. In S518, the analysis support server 104 presents an answer to user 500 based on the analysis results, in the same manner as in S404. As described above, the analysis support server 104 may present the analysis results to the user as they are, or it may process the analysis results before presenting them to the user.

[0056] In S519, the analysis support server 104 requests that the context stored in the analysis instance 502 be copied to the question generation instance 501. In S520, the context stored in the analysis instance 502 is copied to the question generation instance 501. Then, in S521, the same process as in S506-S517 is executed.

[0057] By copying the context of analysis instance 502 to question generation instance 501, candidate questions based on the analysis performed in S516 are generated. If the analysis server 106 does not have the function to manage context, the analysis support server 104 may make a question generation request in the same context as the analysis request by including the contents of the analysis request submitted in S515 in the question generation request in S521. In this case, S515 and S516 are not executed.

[0058] Subsequently, the analysis support server 104 repeats steps S519-S521 each time it obtains an additional question from user 500. The analysis request for the additional question is made within an existing context stored in analysis instance 502. This request is made in a different context from the context used to generate the candidate questions in S521 mentioned above.

[0059] In S522, the analysis support server 104 receives a termination command from user 500. The termination command may be an explicit termination command (such as pressing a termination button) or an implicit termination command (such as closing a browser or the elapsed of a predetermined amount of time).

[0060] In the method shown in Figure 5, the analysis support server 104 presents candidate questions to the user for each question the user asks. Alternatively, the analysis support server 104 may present candidate questions to the user only before the first question the user asks, and not present any more candidate questions thereafter. Alternatively, the analysis support server 104 may not present candidate questions to the user before the first question the user asks, but may present them before the second and subsequent questions.

[0061] The invention is not limited to the embodiments described above, and various modifications and changes are possible within the scope of the gist of the invention. [Explanation of Symbols]

[0062] 100 Analysis System, 101 Management Server, 104 Analysis Support Server, 106 Analysis Server

Claims

1. It is an analysis support server, A first acquisition means for acquiring time-series data related to a device specified by the user, A second acquisition means for obtaining questions regarding the aforementioned time-series data from the user, Input means for inputting an analysis request including the aforementioned time-series data and the aforementioned questions into an analysis server, An analysis support server comprising: a presentation means for presenting answers to the questions to the user based on the analysis results from the analysis server.

2. The analysis support server according to claim 1, wherein the analysis request includes a timestamp associated with the data at each point in time of the time-series data.

3. The analysis support server according to claim 1, wherein the presentation means further presents candidate questions to the user.

4. The input means further inputs the time-series data and a question generation request for generating candidate questions related to the time-series data to the analysis server or another analysis server. The analysis support server according to claim 3, wherein the presentation means presents candidate questions generated by the analysis server or another analysis server to the user.

5. The analysis support server according to claim 4, wherein the question generation request includes past cases based on suggestions from the analysis server or the other analysis server.

6. The analysis support server according to claim 4, wherein the input means inputs the analysis request and the question generation request in separate contexts.

7. The analysis support server according to claim 1, wherein the analysis request specifies the data format of the time-series data.

8. The device is an analysis support server according to claim 1, comprising a sensor.

9. The analysis support server according to claim 1, wherein the second acquisition means further acquires additional questions from the user regarding the answer.

10. A program for causing a computer to function as an analysis support server according to any one of claims 1 to 9.

11. An analysis support method, The first acquisition means includes a first acquisition step of acquiring time-series data relating to a device specified by the user, The second acquisition means includes a second acquisition step of obtaining questions from the user regarding the time-series data, The input means includes an input step of inputting the time-series data and the analysis request including the questions to the analysis server, An analysis support method comprising a presentation step of presenting the user with an answer to the question based on the analysis results from the analysis server.

Images