Water pipe deterioration degree determination program

Abstract

To enable automatic and accurate determination of a degree of deterioration of a water pipe.SOLUTION: A water pipe deterioration degree determination program for determining the degree of deterioration of water piping is provided, the program being configured to make a computer perform: an information acquisition step of acquiring wave motion data detected from a determination target water pipe; and a determination step of utilizing three or more levels of association between reference wave motion data acquired from the water pipe in the past and the degree of deterioration of the water pipe to determine the degree of deterioration of the water pipe by giving priority to ones with higher levels of association, on the basis of the reference wave motion data corresponding to the wave motion data acquired in the information acquisition step.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to a water pipe deterioration degree determination program for determining the deterioration degree of a water pipe. [Background technology]

[0002] Water pipes are an essential infrastructure that forms the lifeline of our daily lives. These water pipes also deteriorate over time and eventually need to be replaced. If we could predict this deterioration in advance, we could effectively renew water pipes and also effectively develop water infrastructure that is earthquake-resistant.

[0003] However, up until now, no system has been devised that can automatically and accurately determine the degree of deterioration of such water pipes. Summary of the Invention [Problem to be solved by the invention]

[0004] The present invention was devised in consideration of the above-mentioned problems, and its purpose is to provide a water pipe deterioration degree determination program that can automatically and accurately determine the degree of deterioration of a water pipe without relying on human labor, even if the user does not have any special skills or experience. [Means for solving the problem]

[0005] The water pipe deterioration degree determination program according to the present invention is a water pipe deterioration degree determination program for determining the deterioration degree of a water pipe, Regarding sound or vibration Wave Data and water leakage history information regarding the water leakage history of the water pipe to be identified. and the information acquisition step to acquire the information acquired from the water pipe in the past. Regarding sound or vibration Reference wave data, A higher correlation is set between a combination having reference water leakage history information relating to the water pipe leakage history and the deterioration degree of the water pipe, using three or more levels of correlation between the combination and the reference wave data corresponding to the wave data acquired in the information acquisition step and the reference water leakage history information corresponding to the water leakage history information. and a determination step of determining the degree of deterioration of the water pipe. The above correlations are composed of nodes in a neural network in artificial intelligence. It is characterized by: [Effects of the Invention]

[0006] Even without special skills or experience, the degree of deterioration of water pipes can be determined automatically and with high accuracy without relying on human labor. [Brief explanation of the drawings]

[0007] [Figure 1] 1 is a block diagram showing the overall configuration of a system to which the present invention is applied. [Figure 2] FIG. 2 is a diagram illustrating a specific configuration example of a search device. [Figure 3] FIG. 10 is a diagram for explaining the operation of the present invention. [Figure 4] FIG. 10 is a diagram for explaining the operation of the present invention. [Figure 5] FIG. 10 is a diagram for explaining the operation of the present invention. [Figure 6] FIG. 10 is a diagram for explaining the operation of the present invention. [Figure 7] FIG. 10 is a diagram for explaining the operation of the present invention. [Figure 8] FIG. 10 is a diagram for explaining the operation of the present invention. [Figure 9] FIG. 10 is a diagram for explaining the operation of the present invention. [Figure 10] FIG. 10 is a diagram for explaining the operation of the present invention. [Figure 11] FIG. 10 is a diagram for explaining the operation of the present invention. [Figure 12] FIG. 10 is a diagram for explaining the operation of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0008] A water pipe deterioration degree determination program to which the present invention is applied will be described in detail below with reference to the drawings.

[0009] First embodiment 1 is a block diagram showing the overall configuration of a water pipe deterioration degree determination system 1 in which a water pipe deterioration degree determination program according to the present invention is implemented. The water pipe deterioration degree determination system 1 includes an information acquisition unit 9, a search device 2 connected to the information acquisition unit 9, and a database 3 connected to the search device 2.

[0010] The information acquisition unit 9 is a device through which users of the system input various commands and information. Specifically, the information acquisition unit 9 includes a keyboard, buttons, a touch panel, a mouse, switches, etc. The information acquisition unit 9 is not limited to a device for inputting text information, but may also include a device capable of detecting voice and converting it into text information, such as a microphone. The information acquisition unit 9 may also be configured as an imaging device capable of capturing images, such as a camera. The information acquisition unit 9 may also be configured as a scanner capable of recognizing character strings from paper documents. The information acquisition unit 9 may also be integrated with the search device 2, which will be described later. The information acquisition unit 9 outputs the detected information to the search device 2. The information acquisition unit 9 may also be configured as a means for identifying location information by scanning map information. The information acquisition unit 9 may also be configured as a temperature sensor, a humidity sensor, a wind direction sensor, and an illuminance sensor for measuring temperature, humidity, wind direction, and light. The information acquisition unit 9 may also be configured as a communication interface for acquiring weather data from the Japan Meteorological Agency or private weather forecasting companies. The information acquisition unit 9 may also be configured as a body sensor worn on the body to detect body data, and this body sensor may be configured as a sensor for detecting, for example, body temperature, heart rate, blood pressure, number of steps, walking speed, and acceleration. The body sensor may also be configured to acquire biometric data of not only humans but also animals. The information acquisition unit 9 may also be configured as a device that acquires information by scanning information such as drawings or reading it from a database. In addition to these, the information acquisition unit 9 may also be configured as an odor sensor that detects odors and fragrances.

[0011] Various information necessary for making policy proposals is stored in database 3. The information necessary for making policy proposals includes the reference information, wave data, and flow rate data described below, stored in relation to the degree of deterioration of water pipes as output data and the policies to be proposed.

[0012] That is, the database 3 stores one or more of such reference information, wave data, and flow rate data, in association with the degree of deterioration of water pipes and policies to be proposed.

[0013] The search device 2 is configured with an electronic device such as a personal computer (PC), but may also be realized with any other electronic device other than a PC, such as a mobile phone, a smartphone, a tablet terminal, a wearable terminal, etc. The user can obtain a search solution by this search device 2.

[0014] 2 shows a specific example of the configuration of the search device 2. In this search device 2, a control unit 24 for controlling the entire search device 2, an operation unit 25 for inputting various control commands via operation buttons, a keyboard, etc., a communication unit 26 for performing wired or wireless communication, a discrimination unit 27 for making various decisions, and a memory unit 28, represented by a hard disk or the like, for storing programs for performing searches to be executed, are all connected to an internal bus 21. Furthermore, a display unit 23 serving as a monitor for actually displaying information is connected to this internal bus 21.

[0015] The control unit 24 is a so-called central control unit that controls each component implemented in the search device 2 by transmitting a control signal via the internal bus 21. In addition, the control unit 24 transmits various control commands via the internal bus 21 in response to operations via the operation unit 25.

[0016] The operation unit 25 is embodied by a keyboard or a touch panel, and an execution command for executing a program is input by the user. When the execution command is input by the user, the operation unit 25 notifies the control unit 24. Upon receiving this notification, the control unit 24 executes the desired processing operation in cooperation with the determination unit 27 and other components. The operation unit 25 may be embodied as the information acquisition unit 9 described above.

[0017] The discrimination unit 27 discriminates the search solution. When performing the discrimination operation, the discrimination unit 27 reads out various pieces of information stored in the storage unit 28 as necessary information and various pieces of information stored in the database 3. The discrimination unit 27 may be controlled by artificial intelligence. The artificial intelligence may be based on any well-known artificial intelligence technology.

[0018] The display unit 23 is configured by a graphic controller that creates a display image under the control of the control unit 24. The display unit 23 is realized by, for example, a liquid crystal display (LCD) or the like.

[0019] When the storage unit 28 is configured as a hard disk, predetermined information is written to each address and read out as necessary under the control of the control unit 24. The storage unit 28 also stores a program for carrying out the present invention. The program is read out and executed by the control unit 24.

[0020] The operation of the water pipe deterioration degree determination system 1 configured as described above will be described below.

[0021] The water pipe deterioration level determination system 1 is based on the premise that three or more levels of correlation between the reference wave data and the deterioration level of the water pipe are preset, as shown in FIG. 3, for example. Water pipes include any pipe through which water flows, regardless of whether it is a water supply system, sewerage system, or industrial plant. The reference wave data is data consisting of electromagnetic waves, light waves, sound waves, vibrations, etc. emitted from or reflected by the water pipe. The sound waves may be data of sounds from the water pipe. They may also be time-series recordings of sounds emitted as water flows through the water pipe. They may also be data acquired by a sensor attached to the water pipe that can detect sound waves. The vibrations are vibration waves that occur when the water pipe vibrates as water flows through it. Regarding the method for detecting vibration waves, in addition to vibration sensors and strain sensors, ultrasonic sensors or the like may be used to detect the vibrations if they are expressed as sound waves. The wave data consisting of electromagnetic waves and light may also be composed of ordinary image data or spectral data. The reference wave data includes any wave-based data used in non-destructive testing.

[0022] These reference wave data can be managed in any time-series unit, such as yearly, monthly, weekly, daily, hourly, or minutely.

[0023] The deterioration degree may be expressed as a percentage or the like, but is not limited to this. The deterioration degree may be expressed in three stages: high, normal, and low, or in two stages: replacement required and no replacement required. The deterioration degree may also be composed of information regarding the deterioration status, such as information indicating a certain percentage of corrosion or the presence of solid masses inside the water pipe. Such an evaluation of the deterioration degree may be an actual assessment by an expert or professional in the field.

[0024] 3, the input data are assumed to be reference wave data P01, P02, and P03. Such reference wave data P01, P02, and P03 as input data are linked to the degree of deterioration as output.

[0025] The reference wave data P01, P02, and P03 are correlated with each other through three or more levels of correlation with the deterioration degrees A to D as the output solution. The deterioration degrees are indicated, for example, such that A is 95% deterioration and B is 60% deterioration. The reference wave data are arranged on the left side according to the correlation degrees, and the deterioration degrees are arranged on the right side according to the correlation degrees. The correlation degrees indicate the degree of correlation with which deterioration degree each reference wave data arranged on the left side is highly related. In other words, the correlation degrees are indices that indicate the likelihood of each reference wave data being associated with which deterioration degree, and indicate the accuracy in selecting the most likely deterioration degree for each reference wave data. In the example of FIG. 3, correlation degrees w13 to w19 are shown. These w13 to w19 are shown on a 10-point scale as shown in Table 1 below. The closer to 10 points, the more closely each combination of intermediate nodes is related to the degree of deterioration as an output. Conversely, the closer to 1 point, the less closely each combination of intermediate nodes is related to the degree of deterioration as an output.

[0026] [Table 1]

[0027] The search device 2 acquires in advance three or more levels of correlation w13 to w19 as shown in Fig. 3. That is, when determining an actual search solution, the search device 2 accumulates past data sets, including which reference wave data and the degree of deterioration in each case were adopted and evaluated, and analyzes these to create the correlation shown in Fig. 3. Note that the reference wave data is not limited to time-series data, but may be data that has been FFT-transformed and converted into a frequency domain.

[0028] This analysis may be performed by artificial intelligence. In such a case, each reference wave data and a data set of the deterioration degree in that case are trained. In the case of wave data P01, if there are many cases of deterioration degree A, the correlation degree leading to the evaluation of this deterioration degree is set higher, and if there are many cases of deterioration degree B, the correlation degree leading to the evaluation of this deterioration degree is set higher. For example, in an example of reference wave data for wave data P01, deterioration degree A is linked to deterioration degree C, but the correlation degree of w13, which is connected to deterioration degree A from previous cases, is set to 7 points, and the correlation degree of w14, which is connected to deterioration degree C, is set to 2 points.

[0029] The correlation shown in Fig. 3 may be configured by nodes of a neural network in artificial intelligence. That is, the weighting coefficients for the outputs of the nodes of this neural network correspond to the correlation described above. Furthermore, the correlation is not limited to a neural network, and may be configured by any decision-making factors that constitute artificial intelligence.

[0030] In such a case, as shown in Figure 4, reference wave data for each region may be input as input data, and the degree of deterioration may be output as output data, with at least one hidden layer provided between the input node and the output node for machine learning. The above-mentioned correlation degree may be set in either or both of the input node and the hidden layer node, and this becomes the weighting of each node, and output selection is based on this. Then, when this correlation degree exceeds a certain threshold, that output may be selected.

[0031] Such correlations are what is called "learned data" in artificial intelligence. After creating such learned data, when actually determining a new degree of deterioration, the learned data described above will be used to search for the degree of deterioration. It may be possible to determine which of the pre-defined classifications of the degree of deterioration the item falls into.

[0032] When a new deterioration degree is to be searched for, wave data is input. Details of the wave data will be omitted below, and the explanation will be given in the above-mentioned description of the reference wave data.

[0033] Next, this input wave data is compared with the reference wave data. In such cases, the correlation degrees shown in Figure 3 (Table 1) obtained in advance are referenced. For example, if the newly obtained wave data is identical to or similar to P02, the deterioration degree B is associated with the deterioration degree C at a correlation degree of w15 and the deterioration degree C at a correlation degree of w16. In such a case, the deterioration degree B, which has the highest correlation degree, is selected as the optimal solution. However, it is not essential to select the one with the highest correlation degree as the optimal solution; the deterioration degree C, which has a low correlation degree but is recognized as being correlated, may be selected as the optimal solution. Furthermore, it is of course possible to select an output solution other than this that does not have a connecting arrow, and any other priority order may be used as long as it is based on the correlation degree.

[0034] Incidentally, when comparing the wave data with the reference wave data, if these data are expressed as average values ​​over a certain period, it may be possible to determine whether they are identical or similar based on whether the average values ​​are within a range of ±10%. Also, if the wave data is shown as a time-series transition graph, it may be possible to determine whether they are identical or similar based on the similarity of their trends.

[0035] In this way, the most suitable deterioration level can be found from the newly acquired wave data and displayed to the user. By looking at the search results, it is possible to determine in advance what the future deterioration level in that area will be. The proposed deterioration level can be used as a reference when formulating new policies.

[0036] The example in Figure 5 shows an example in which a correlation is formed between a combination of reference wave data and reference flow rate data. The reference flow rate data is data related to the flow rate of a water pipe. The flow rate of a water pipe may be composed of data obtained by a flow meter attached to the water pipe, or data sensed by the flow meter obtained via wireless communication. The reference flow rate data may be composed of data obtained by performing various statistical processes on the flow rate measured per unit time, or may be composed of an average value, or may be composed of a standard deviation of the flow rate measured over time. The reference flow rate data may also be composed of the change trend of the flow rate measured over time itself, or a typology of these.

[0037] The degree of deterioration depends on the flow rate data as well as the wave data. Therefore, by combining the reference wave data and the reference flow rate data with the learning data, the degree of deterioration can be determined with higher accuracy. Therefore, the above-mentioned correlation is formed by combining the reference wave data and the reference flow rate data.

[0038] In the example of Fig. 5, the input data is assumed to be, for example, reference wave data P01 to P03 and reference flow rate data P14 to P17. The intermediate nodes shown in Fig. 5 are formed by combining the reference wave data as input data with the reference flow rate data. Each intermediate node is further connected to an output. In this output, the degree of deterioration is displayed as an output solution.

[0039] Each combination (intermediate node) of reference wave data and reference flow rate data is related to each other through three or more levels of correlation with respect to the degree of deterioration as the output solution. The reference wave data and reference flow rate data are arranged on the left side via this correlation, and the degree of deterioration is arranged on the right side via this correlation. The correlation indicates the degree of correlation between the reference wave data and reference flow rate data arranged on the left side and the degree of deterioration. In other words, this correlation is an index that indicates the likelihood that each reference wave data and reference flow rate data will be linked to a degree of deterioration, and indicates the accuracy in selecting the most likely degree of deterioration from the reference wave data and reference flow rate data. Therefore, the optimal degree of deterioration is searched for by combining these reference wave data and reference flow rate data.

[0040] In the example of Figure 5, w13 to w22 are shown as the degrees of association. These w13 to w22 are shown on a 10-point scale as shown in Table 1, with the closer to 10 points the higher the degree of association between each combination as an intermediate node and the output, and conversely, the closer to 1 point the lower the degree of association between each combination as an intermediate node and the output.

[0041] The search device 2 acquires in advance three or more levels of correlation w13 to w22 as shown in Fig. 5. In other words, when determining an actual search solution, the search device 2 accumulates past data on which reference wave data and reference flow rate data, as well as which of the data corresponds to the degree of deterioration in each case, and analyzes and interprets these to create the correlations shown in Fig. 5.

[0042] This analysis may be performed by artificial intelligence. In such a case, for example, when the reference wave data P01 is the reference flow rate data P16, the degree of deterioration is analyzed from past data. If there are many cases of deterioration degree A, the correlation degree leading to deterioration degree A is set higher, and if there are many cases of deterioration degree B and few cases of deterioration degree A, the correlation degree leading to deterioration degree B is set higher and the correlation degree leading to deterioration degree A is set lower. For example, in the example of intermediate node 61a, which is linked to the outputs of deterioration degree A and deterioration degree B, the correlation degree of w13, which is connected to deterioration degree A from previous cases, is set to 7 points, and the correlation degree of w14, which is connected to deterioration degree B, is set to 2 points.

[0043] The correlation shown in Figure 5 may be configured by nodes of a neural network in artificial intelligence. That is, the weighting coefficients for the output of the nodes of this neural network correspond to the correlation described above. Furthermore, it is not limited to a neural network, and may be configured by any decision-making factors that constitute artificial intelligence. Other configurations related to artificial intelligence are the same as those described in Figure 4.

[0044] 5, node 61b is a node for the combination of reference wave data P01 and reference flow rate data P14, and the degree of association for deterioration degree C is w15 and the degree of association for deterioration degree E is w16. Node 61c is a node for the combination of reference wave data P02 and reference flow rate data P15 and P17, and the degree of association for deterioration degree B is w17 and the degree of association for deterioration degree D is w18.

[0045] This correlation becomes what is called learned data in artificial intelligence. After creating this learned data, the above-mentioned learned data will be used when actually determining the degree of deterioration. In such cases, the region for which the degree of deterioration is to be determined is entered in the same way. Then, wave data and flow rate data organized for each region in database 3 are obtained.

[0046] In this way, the optimum deterioration degree is searched for based on the newly acquired wave data and flow data. In such cases, the previously acquired correlations shown in FIG. 5 (Table 1) are referenced. For example, if the newly acquired wave data is identical to or similar to P02 and the flow data is identical to or similar to P17, node 61d is associated via the correlation, and this node 61d is associated with deterioration degree C at w19 and deterioration degree D at w20. In such a case, deterioration degree C, which has the highest correlation, is selected as the optimum solution. However, it is not essential to select the one with the highest correlation as the optimum solution; deterioration degree D, which has a low correlation but is recognized as having correlation, may be selected as the optimum solution. Furthermore, it is of course possible to select an output solution other than this that is not connected by an arrow, and any other priority order may be used as long as it is based on the correlation.

[0047] Table 2 below shows examples of the degrees of association w1 to w12 extending from the input.

[0048] [Table 2]

[0049] The intermediate node 61 may be selected based on the degrees of association w1 to w12 extending from this input. In other words, the greater the degrees of association w1 to w12, the heavier the weighting in selecting the intermediate node 61. However, the degrees of association w1 to w12 may all have the same value, and the weighting in selecting the intermediate node 61 may all be the same.

[0050] According to the present invention, in addition to the reference wave data described above, a solution search may be performed based on a combination of reference water pressure data relating to the water pressure of water pipes acquired in the past instead of the reference flow rate data described above, and three or more levels of correlation between the combination and the degree of deterioration.

[0051] This reference water pressure data, which is added as an explanatory variable instead of the reference flow rate data, is data related to the water pressure of the water pipe. The water pressure of the water pipe may be composed of data obtained by a water pressure gauge attached to the water pipe, or data sensed by the water pressure gauge and acquired via wireless communication. The reference water pressure data may be composed of various statistically processed data on the water pressure measured per unit time, or may be composed of an average value, or may be composed of the standard deviation of the water pressure measured over time. It may also be composed of the change trend of the water pressure measured over time itself, or a typology of these.

[0052] Since the water pressure of such water pipes also affects the degree of deterioration, the accuracy of the determination can be improved by combining it with reference wave data and determining the degree of deterioration through the correlation. When searching for a solution, wave data and water pressure data of the water pipe to be determined are actually acquired. The optimal degree of deterioration is determined based on the newly acquired wave data and water pressure data. In such cases, the degree of deterioration is determined based on the method described above, referring to the correlation obtained in advance.

[0053] According to the present invention, in addition to the reference wave data described above, a solution search may be performed based on a combination of reference leakage history information regarding the leakage history of a water pipe instead of the reference flow rate data described above, and three or more levels of correlation between the combination and the degree of deterioration.

[0054] This reference water leakage history information, which is added as an explanatory variable instead of the reference flow rate data, includes all information related to the water leakage history of the water pipe. If the water pipe has never had a leak before or if a leak has occurred in the past, the reference water leakage history information includes information on the date and time of the leak, the number of times, the extent of the leak, etc.

[0055] When searching for a solution, wave data and water leakage history information are actually acquired for the water pipe whose deterioration level is to be determined. The optimal deterioration level is searched for based on the newly acquired wave data and water leakage history information. In such cases, the previously acquired correlation is referenced and the deterioration level is searched for based on the above-mentioned method.

[0056] According to the present invention, in addition to the reference wave data described above, a solution search may be performed based on a combination of reference pavement information regarding the pavement condition of the road on which the water pipe is laid instead of the reference flow rate data described above, and three or more levels of correlation between the combination and the degree of deterioration.

[0057] The reference pavement information, which is added as an explanatory variable instead of the reference flow data, includes all information regarding the pavement condition of the road on which the water pipe is installed. A road on which a water pipe is installed includes the road directly above the water pipe if the water pipe is underground. The pavement condition may be indicated not only by whether the road is paved or not, but also by the year the pavement was installed if paved, and, if the pavement has been renewed, by the year of renewal. The pavement condition may also be determined by capturing an image of the road with a camera and analyzing the image. The image may also be a spectral image captured with a spectral camera. When performing this image analysis, the determination may be based on previously trained features. In this case, artificial intelligence may be used to train a dataset of image data and road surface roughness, and when the reference pavement information is actually acquired, the pavement condition may be determined by comparing the learned image data with the acquired image data.

[0058] When searching for a solution, wave data on the water pipe whose deterioration level is to be determined and pavement information on the pavement condition of the road on which the water pipe is laid are acquired. When acquiring the pavement information, the above-mentioned image analysis, or even artificial intelligence, may be used to make the determination. Next, the optimal deterioration level is searched for based on the newly acquired wave data and pavement information. In such a case, the previously acquired correlation is referenced and the deterioration level is searched for based on the above-mentioned method.

[0059] According to the present invention, in addition to the reference wave data described above, a solution search may be performed based on a combination of reference traffic volume information relating to the traffic volume of roads on which water pipes are laid instead of the reference flow rate data described above, and three or more levels of correlation between the combination and the degree of deterioration.

[0060] This reference traffic volume information, which is added as an explanatory variable instead of the reference flow data, includes all information related to the traffic volume of the road on which the water pipe is laid. The reference traffic volume information is information related to the volume of vehicles or pedestrians passing on the road. This traffic volume is the number of vehicles or pedestrians passing per unit time. Since water pipes laid on roads with heavy traffic deteriorate more quickly, this is included in the explanatory variables for judgment.

[0061] Such reference traffic volume information and traffic volume information may directly use data from traffic volume surveys conducted by municipalities, the national government, or other organizations, or may be determined based on images of roads captured per unit time. In such cases, an inspector may count the number of vehicles and pedestrians in the images one by one, or well-known deep learning technology may be used to extract and identify vehicles and pedestrians, and the number of identified vehicles and pedestrians per unit time may be counted.

[0062] When searching for a solution, wave data on the water pipe whose deterioration level is to be determined and traffic volume information on the traffic volume on the road where the water pipe is laid are actually acquired. When acquiring the traffic volume information, the above-mentioned image analysis, or even deep learning technology, may be used to make the determination. Next, the optimal deterioration level is searched for based on the newly acquired wave data and traffic volume information. In such a case, the previously acquired correlation is referenced and the deterioration level is searched for based on the above-mentioned method.

[0063] In addition, according to the present invention, in addition to the above-mentioned reference wave data, a solution search may be performed based on a combination of reference attribute information instead of the above-mentioned reference flow data and three or more levels of correlation between the degree of deterioration for that combination.

[0064] This reference attribute information, added as an explanatory variable in place of the reference flow data, includes the age, health status, annual income, date of birth, hometown, and family environment of people who live, work, or pass through the building structure where the water pipe is installed. It also includes, if children are currently attending school, their tuition fees and expected future tuition fees, and whether the individual is currently job-hunting or employed. Health status includes all kinds of information indicating the individual's health, such as whether they are completely healthy, whether they have any congenital disabilities and the severity of those disabilities, whether they have any acquired disabilities after birth and the severity of those disabilities, whether they have had any illnesses since birth, whether those illnesses continue to exist and the severity of those illnesses, their allergies, inflammation, injuries, chronic illnesses, and medication status. The health status included in this reference attribute information may be derived from medical data itself, such as heart rate, pulse rate, blood data, electrocardiogram data, and X-ray images. These may also be obtained through household reports, submitted documents, doctor's certificates, and other sources. When this reference attribute information is applied to the above-mentioned reference information P34 to P36, for example, reference information P34 may be: age 46, hometown: Shizuoka, annual income XX yen, working for XX company, family environment: family of four (wife, eldest son, and eldest daughter), eldest son is in high school and eldest daughter is in junior high school, health condition: has had surgery for stomach ulcer in the past, and reference information P35 may be: age 38, hometown: Tokyo, annual income XX yen, working for XX company, family environment: family of three (wife and eldest daughter), eldest daughter is in elementary school, health condition: good, etc.

[0065] Reference attribute information and attribute information are all information related to the corporation that exists in the building structure. Attributes here include, but are not limited to, the corporation's industry, technology field, history, background, capital, size, number of employees, and years since establishment, as well as corporate culture, employee morale, and number of employees.

[0066] Such reference attribute information and attribute information may be obtained from databases managed for each region or country, or from public information in the case of statistical data, but it is also possible to determine the age, gender, etc. of people shown in images captured by surveillance cameras installed on the road through image analysis, and obtain this as reference attribute information and attribute information.

[0067] When searching for a solution, wave data and attribute information for the area whose deterioration level is to be determined are actually acquired. The optimal deterioration level is searched for based on the newly acquired wave data and attribute information. In such cases, the previously acquired correlation level is referenced, and the deterioration level is searched for based on the above-mentioned method.

[0068] In the above-mentioned correlation degree, the correlation degree is expressed on a 10-point scale, but it is not limited to this and may be expressed on a scale of 3 or more, and conversely, if it is 3 or more, it may be expressed on a scale of 100 or 1000. On the other hand, this correlation degree does not include a 2-point scale, that is, a scale expressed by either 1 or 0, indicating whether or not there is a correlation between the two.

[0069] According to the present invention having the above-mentioned configuration, anyone can easily determine and search for the deterioration level of water pipes, even without special skills or experience. Furthermore, according to the present invention, it is possible to judge the search solution with higher accuracy than a human would. Furthermore, by configuring the above-mentioned correlation using artificial intelligence (such as a neural network), it is possible to further improve the accuracy of the determination by learning this.

[0070] In addition, since there are many cases where the above-mentioned input data and output data do not exist exactly the same during the learning process, the input data and output data may be classified by type. In other words, the information P01, P02, ..., P15, 16, ... that constitutes the input data may be classified according to classification criteria previously determined by the system or user depending on the content of the information, and a data set may be created using the classified input data and output data, and learning may be performed.

[0071] Furthermore, the present invention determines the degree of deterioration based on the correlation between a combination of two or more types of information, namely, reference information U and reference information V, as shown in Fig. 6. The reference information U is reference wave data, and the reference information V is any other reference information other than the reference wave data.

[0072] At this time, the output obtained for the reference information U may be used as input data as it is, and may be associated with the output (degree of deterioration) via an intermediate node 61 in combination with the reference information V. For example, after an output solution is obtained for the reference information U (reference wave data) as shown in Fig. 3, this may be used as input as it is, and the output (degree of deterioration) may be searched for using the correlation with other reference information V.

[0073] Furthermore, the present invention is characterized in that an optimal solution is searched for through correlation levels set to three or more levels. The correlation level can be expressed, for example, by a numerical value from 0 to 100%, in addition to the above-mentioned 10 levels, but is not limited to this and may be configured in any level as long as it can be expressed by a numerical value of three or more levels.

[0074] By determining the most likely degree of deterioration based on the correlation expressed in three or more levels, it becomes possible to search and display solutions in descending order of correlation when multiple potential solutions are considered. By displaying solutions to the user in descending order of correlation, it becomes possible to prioritize the display of more likely solutions.

[0075] In addition, according to the present invention, it is possible to judge without overlooking even a discrimination result with an extremely low output, such as a correlation degree of 1%, and it is possible to alert the user that even a discrimination result with an extremely low correlation degree is connected as a slight sign, and that it may be useful as a discrimination result once in tens or hundreds of times.

[0076] Furthermore, according to the present invention, by performing a search based on such three or more levels of correlation, there is an advantage in that the search policy can be determined by how the threshold is set. A low threshold can detect even cases with a correlation of 1% without omission, but the possibility of detecting a more appropriate discrimination result is low and a lot of noise may be picked up. On the other hand, a high threshold can detect the optimal search solution with a high probability, but it may miss a suitable solution that usually has a low correlation and is ignored, but appears once in tens or hundreds of times. The emphasis can be decided based on the user's or system's perspective, and it is possible to increase the degree of freedom in selecting the points to be emphasized.

[0077] Furthermore, in the present invention, the correlation degree may be updated. This update may be made to reflect information provided via a public communication network such as the Internet. Furthermore, when reference information such as reference wave data is acquired and knowledge, information, or data relating to the degree of deterioration of the reference information is acquired, the correlation degree may be increased or decreased accordingly.

[0078] In such a case, cases of whether or not the reference information, including the reference wave data, actually occurred and the results of the discrimination of the risk level and signs are collected, and the correlation degree is increased or decreased according to the number of cases. At this time, information corresponding to the reference information, including the above-mentioned wave data, may be acquired, and when discrimination is made, the correlation degree may be updated based on this.

[0079] In other words, this update corresponds to learning in artificial intelligence. Since new data is acquired and reflected in the learned data, it can be considered a learning process.

[0080] Furthermore, the process of initially creating a trained model and the above-mentioned updates may use not only supervised learning, but also unsupervised learning, deep learning, reinforcement learning, etc. In the case of unsupervised learning, instead of reading and learning a data set of input data and output data, information corresponding to the input data may be read and learned, and then the correlation related to the output data may be self-formed from the information.

[0081] Second embodiment The second embodiment will be described below. In carrying out this second embodiment, the deterioration degree suggestion system 1, information acquisition unit 9, search device 2, and database 3 used in the first embodiment are used in the same manner. The explanation of each of these components will be omitted below by quoting the explanation of the first embodiment.

[0082] In the second embodiment, instead of focusing on one water pipe and determining its deterioration level, the deterioration level of each water pipe in a discrimination target area is determined. The discrimination target area may be configured in any unit of size, for example, it may be configured in a range of a radius of several meters to several kilometers centered on a certain point. The discrimination target area may also be an area in units of a city, ward, town, village, or address. The discrimination is not limited to determining the deterioration levels of all water pipes buried underground in the discrimination target area, but may be limited to determining only a portion of them.

[0083] In such cases, first, reference satellite image information and a data set of the degree of degradation are trained. The reference satellite image information and satellite image information are composed of satellite images taken from an artificial satellite so as to include the area. This reference satellite image information and satellite image information may be any information other than satellite images, as long as it is composed of data obtained by emitting electromagnetic waves from a satellite and acquiring their reflection characteristics.

[0084] 7, the input data is assumed to be reference satellite image information P01, P02, and P03 for each region. Such reference satellite image information P01, P02, and P03 as input data is linked to the degree of deterioration as output.

[0085] The reference satellite image information P01, P02, and P03 are correlated with each other through three or more levels of correlation with respect to the degradation levels A to B as the output solution. The reference satellite image information is arranged on the left side via this correlation level, and the respective degradation levels are arranged on the right side via this correlation level. The correlation level indicates the degree to which the reference satellite image information arranged on the left side is highly related to which degradation level. In other words, the correlation level is an index that indicates the likelihood that each piece of reference satellite image information is associated with which degradation level, and indicates the accuracy of selecting the most likely degradation level for each piece of reference satellite image information.

[0086] This correlation may be formed by a node of a neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the correlation. Furthermore, it is not limited to a neural network, and may be formed by any decision-making factor that constitutes artificial intelligence.

[0087] This correlation is what is called "learned data" in artificial intelligence. After creating this learned data using a data set of previous reference satellite image information for each region and the degree of deterioration, the degree of deterioration is searched for using the learned data when actually determining the degree of deterioration. These data sets may be created by reading them from a database managed by a contractor. The solution search method is the same as in the first embodiment, so a detailed explanation will be omitted.

[0088] The example in Figure 8 shows an example in which a correlation is formed between a combination of reference satellite image information and reference weather information. The reference weather information and weather information indicate information such as the weather (clear, cloudy, rainy), disasters (typhoons, heavy rain, etc.), temperature, and humidity at the time of photography. In addition to this, they may be made up of any data related to wind direction, wind speed, thunderstorms, typhoons, droughts, etc. The reference weather information and weather information may be obtained by importing the weather at that time from data from the Japan Meteorological Agency, or by inputting the weather as understood by the user.

[0089] The degree of deterioration of water pipes in the area to be determined depends on weather information as well as satellite image information. Therefore, by combining reference weather information with learning data in addition to reference satellite image information, the degree of deterioration can be determined with higher accuracy. For this reason, the above-mentioned correlation degree is formed by combining reference weather information with reference satellite image information.

[0090] In the example of Fig. 8, the input data is assumed to be, for example, reference satellite image information P01 to P03 and reference weather information P14 to P17. The intermediate nodes shown in Fig. 8 are formed by combining the reference satellite image information as input data with the reference weather information. Each intermediate node is further connected to an output. In this output, the degree of degradation is displayed as an output solution.

[0091] Each combination (intermediate node) of reference satellite image information and reference weather information is related to the degree of degradation as the output solution through three or more levels of correlation. The reference satellite image information and reference weather information are arranged on the left side via this correlation, and the degree of degradation is arranged on the right side via this correlation. The correlation indicates the degree of relevance of the degree of degradation to the reference satellite image information and reference weather information arranged on the left side. In other words, this correlation is an index that indicates the likelihood of each reference satellite image information and reference weather information being linked to a degree of degradation, and indicates the accuracy of selecting the most likely degree of degradation from the reference satellite image information and reference weather information. Therefore, the optimal degree of degradation is searched for by combining these reference satellite image information and reference weather information.

[0092] In the example of Figure 8, w13 to w22 are shown as the degrees of association. These w13 to w22 are shown on a 10-point scale as shown in Table 1, with the closer to 10 points the higher the degree of association between each combination as an intermediate node and the output, and conversely, the closer to 1 point the lower the degree of association between each combination as an intermediate node and the output.

[0093] The search device 2 acquires in advance three or more levels of correlation w13 to w22 as shown in Fig. 8. That is, when determining an actual search solution, the search device 2 accumulates past data on which reference satellite image information and reference weather information, as well as which is the appropriate level of deterioration in each case, and analyzes and interprets these to create the correlations shown in Fig. 8.

[0094] The correlation shown in Fig. 8 may be configured by the nodes of a neural network in artificial intelligence. That is, the weighting coefficients for the output of the nodes of this neural network correspond to the correlations described above. Furthermore, the correlations are not limited to neural networks, and may be configured by any decision-making factors that constitute artificial intelligence. Other configurations related to artificial intelligence are the same as those described in Figs. 4 and 5.

[0095] 8, node 61b is a node for the combination of reference satellite image information P01 and reference weather information P14, and the degree of association for deterioration level C is w15 and the degree of association for deterioration level E is w16. Node 61c is a node for the combination of reference weather information P15 and P17 for reference satellite image information P02, and the degree of association for deterioration level B is w17 and the degree of association for deterioration level D is w18.

[0096] This correlation becomes what is called "trained data" in artificial intelligence. After creating this trained data, the trained data described above will be used when actually determining the degree of deterioration. In such cases, the area for which the degree of deterioration is to be determined is input in the same way. Then, satellite image information and weather information organized for each area in database 3 are obtained.

[0097] In this way, the optimum deterioration degree is searched for based on the newly acquired satellite image information and weather information. In such cases, the previously acquired correlations shown in FIG. 8 (Table 1) are referenced. For example, if the newly acquired satellite image information is identical to or similar to P02 and the weather information is identical to or similar to P17, node 61d is associated via the correlation, and this node 61d is associated with a deterioration degree C of w19 and a deterioration degree D of w20. In such a case, the deterioration degree C, which has the highest correlation, is selected as the optimum solution. However, it is not essential to select the one with the highest correlation as the optimum solution; the deterioration degree D, which has a low correlation but is recognized as being correlated, may be selected as the optimum solution. Of course, an output solution not connected by an arrow may also be selected, and any other priority may be selected based on the correlation.

[0098] According to the present invention, in addition to the above-mentioned reference satellite image information, a solution search may be performed based on a combination of reference soil information on the soil in the determination target area where water pipes are laid instead of the above-mentioned reference weather information, and three or more levels of correlation between the combination and the degree of deterioration.

[0099] This reference soil information, which is added as an explanatory variable instead of the reference weather information, includes all information related to the soil in the area to be determined where the water pipe is installed. Examples of reference soil information include soil components, pH, water content, temperature, etc. The results of actually collecting soil components and analyzing them using chemical analysis methods may be used, or data detected by a well-known soil sensor may be used. Images of the soil taken with a camera, or images extracted using well-known deep learning technology to extract only characteristic parts of the image, may also be used. In addition to the above, the reference soil information may also include measurements of the hardness of the ground, for example, from a boring survey.

[0100] When searching for a solution, satellite image information of the area to be judged for the degree of deterioration and soil information of the area to be judged where the water pipe is laid are acquired. Next, the optimal degree of deterioration is searched for based on the newly acquired satellite image information and soil information. In such cases, the degree of deterioration is searched for based on the method described above, with reference to the correlation degree acquired in advance.

[0101] According to the present invention, in addition to the above-mentioned reference satellite image information, a solution search may be performed based on a combination of reference regional information relating to the area in the determination target area where water pipes are laid instead of the above-mentioned reference weather information, and three or more levels of correlation between the degree of deterioration for the combination.

[0102] This reference area information, which is added as an explanatory variable instead of reference weather information, can be a grouping such as the Kanto region or Tokyo, or can be subdivided at the city, ward, town, or street address level. With regions grouped and subdivided in this way, the business climate, events, accidents, incidents, disasters, infectious diseases, etc. in each segmented area are reflected as this reference area information. For example, reference information P34 may indicate that an incident occurred in Chiyoda Ward, Tokyo, and reference information P35 may indicate that Nara Prefecture has an business climate index of XXXX.

[0103] When searching for a solution, satellite image information of the area to be judged for the degree of deterioration and area information of the area to be judged where the water pipe is laid are acquired. Next, the optimal degree of deterioration is searched for based on the newly acquired satellite image information and area information. In such a case, the degree of deterioration is searched for based on the above-mentioned method, referring to the correlation degree acquired in advance.

[0104] In addition to the above, the reference information in this second embodiment may also be information that forms a correlation between the reference wave data, reference flow rate data, reference water pressure data, reference water leakage history information, reference pavement information, reference traffic volume information, etc. on a regional basis and the above-mentioned reference satellite image information.

[0105] In addition to the above-mentioned reference satellite image information, a solution search may be performed based on a combination of reference external environment information instead of the above-mentioned reference information and three or more levels of correlation between the degree of deterioration for that combination.

[0106] The external environmental information for reference refers to any information related to the external environment. Examples of external environmental information include economic data (GDP, employment statistics, industrial production index, capital investment, labor force survey, consumer price index, and the Bank of Japan Tankan survey, etc.), household data (household consumption survey, household data, average working hours per week, savings statistics, and annual income statistics, etc.), real estate data (office vacancy rate, unit price per square meter, average rent, land prices, and vacant house data, etc.), and natural environment data (disaster data, temperature data, precipitation data, wind direction data, and humidity data, etc.). In addition to reflecting some or all of these data, the external environmental information may also include information related to politics, economics, society, technological advances, fashions, trends, epidemics, and natural disasters. Furthermore, the external environmental information for reference may be defined by text information, or may be categorized by patterns (e.g., whether GDP growth rate increases rapidly or gradually). Furthermore, the reference external environmental information and environmental information may be indicated by the number of tourists in a particular area, the gross domestic product of a prefecture, or the like.

[0107] When searching for a solution, external environment information for the target area is also acquired in addition to the satellite image information. A solution is searched for based on the newly acquired satellite image information and external environment information. In such cases, the previously acquired correlation is referenced and a solution is searched for based on the method described above.

[0108] The present invention is not limited to the above-described embodiment, and for example, as shown in FIG. 9, three or more levels of correlation between the reference information serving as the base and the degree of deterioration may be used. In such a case, a solution search is performed based on three or more levels of correlation between the reference information according to newly acquired information and the degree of deterioration. The reference information serving as the base can be any of the above-described reference information (reference wave data, reference flow rate data, reference water pressure data, reference leak history information, reference pavement information, reference traffic volume information, reference attribute information, reference satellite image information, reference weather information, reference soil information, reference area information, reference external environment information, etc.).

[0109] Similarly, in these cases, when information corresponding to the reference information used as learning data is input, a solution search is performed based on the above-described method.

[0110] The search solution determined through the association may further be modified or weighted based on other reference information.

[0111] The other reference information referred to here corresponds to any reference information other than the reference information that is the base reference information, when any of the above-mentioned reference information is used as the base reference information.

[0112] For example, assume that one of the other reference information items is a certain reference weather information F, and that in the past, the deterioration degree B was often determined. When new weather information corresponding to such reference weather information F is acquired, a process is performed to increase the weight of the search solution B as the deterioration degree, in other words, a process is set in advance to lead to the search solution B of the deterioration degree.

[0113] For example, let us assume that other reference information G is an analysis result that more strongly suggests search solution C as a deterioration degree, and reference information F is an analysis result that more strongly suggests search solution D as a deterioration degree. After this setting with the reference information, if the actually acquired information is identical to or similar to reference information G, a process is performed to increase the weighting of the deterioration degree C. On the other hand, if the actually acquired information is identical to or similar to reference information F, a process is performed to increase the weighting of the deterioration degree D. In other words, the correlation itself leading to the deterioration degree may be controlled based on the reference information F to H. Alternatively, the deterioration degree may be determined based only on the above-mentioned correlation, and then the obtained search solution may be corrected based on the reference information F to H. In the latter case, the weighting and the degree of deterioration as a search solution are corrected based on the reference information F to H, depending on the system design.

[0114] Furthermore, the reference information is not limited to being composed of one type, and a solution search may be performed based on two or more types of reference information. In such a case, the discrimination type as the search solution obtained through the correlation degree may be modified to be higher as the case is more likely to be linked to the degree of deterioration suggested by the reference information.

[0115] Similarly, as shown in Fig. 10, when forming a correlation between the degree of deterioration and a combination of base reference information and other reference information, the base reference information can be any reference information (reference wave data, reference flow rate data, reference water pressure data, reference water leakage history information, reference pavement information, reference traffic volume information, reference attribute information, reference satellite image information, reference weather information, reference soil information, reference area information, reference external environment information, etc.). The other reference information includes any reference information other than the base reference information.

[0116] In this case, if the basic reference information is reference satellite image information, the other reference information includes any other reference information.

[0117] In such a case, the degree of deterioration can be estimated by performing a solution search in the same manner. At this time, as shown in Fig. 9, the degree of deterioration may be corrected for the search solution obtained through the correlation degree using further other reference information (reference information F, G, H, etc.).

[0118] In this case, the degree of association may be learned by combining not only one piece of other reference information but also two or more pieces of other reference information.

[0119] Furthermore, as shown in Fig. 11, a correlation may be formed between only the basic reference information and the degree of deterioration. Any of the reference information in the first and second embodiments (reference wave data, reference flow rate data, reference water pressure data, reference water leakage history information, reference pavement information, reference traffic volume information, reference attribute information, reference satellite image information, reference weather information, reference soil information, reference area information, reference external environment information, etc.) can be applied to this basic reference information. The solution search method in Fig. 11 will not be described below, but the explanation for Fig. 3 will be cited.

[0120] In the first and second embodiments, the search solution is described as searching for the degree of deterioration, but the present invention is not limited to this. For example, each degree of deterioration may be linked in advance to a water pipe replacement time. In such a case, the water pipe replacement time p is linked to the degree of deterioration A, the water pipe replacement time q is linked to the degree of deterioration B, and the water pipe replacement time r is linked to the degree of deterioration C, and these are stored in advance as a database. The water pipe replacement time here may indicate not only whether the water pipe should be replaced immediately, but also how many days, weeks, months, or years in which the water pipe should be replaced.

[0121] Furthermore, in the first and second embodiments, instead of searching for the degree of deterioration as a search solution, the replacement time of the water pipe may be searched for as shown in Fig. 12. In such a case, the replacement time of the water pipe may be linked to the reference information as an alternative to the degree of deterioration and learned. In such a case, all of the above-mentioned degrees of deterioration can be replaced with the replacement time of the water pipe. [Explanation of symbols]

[0122] 1. Water pipe deterioration level determination system 2 Search device 21 Internal Bus 23 Display section 24 Control Unit 25 Control section 26 Communications Department 27 Discrimination part 28 Memory section 61 nodes

Claims

1. In a water pipe deterioration degree determination program that determines the degree of deterioration of a water pipe, an information acquisition step of acquiring wave data relating to sound or vibration detected from the water pipe to be identified and water leakage history information relating to the water leakage history of the water pipe to be identified; a determination step of determining a deterioration level of a water pipe for which a higher degree of correlation is set between a combination of reference wave data relating to sound or vibration acquired from the water pipe in the past and reference water leakage history information relating to the water leakage history of the water pipe, and a deterioration level of the water pipe, using three or more levels of correlation between the combination and the deterioration level of the water pipe, and the combination of reference wave data corresponding to the wave data acquired in the information acquisition step and reference water leakage history information corresponding to the water leakage history information; The above correlations are composed of nodes in a neural network in artificial intelligence. A program for determining the degree of deterioration of water pipes.

2. In a water pipe deterioration degree determination program that determines the degree of deterioration of a water pipe, an information acquisition step of acquiring wave data relating to sound or vibration detected from the water pipe to be identified and pavement information relating to the pavement condition of the road on which the water pipe to be identified is laid; a determination step of determining a deterioration level of a water pipe for which a higher degree of correlation is set between a combination of reference wave data relating to sound or vibration previously acquired from the water pipe and reference pavement information relating to the pavement condition of the road on which the water pipe is laid, and the deterioration level of the water pipe, using three or more levels of correlation between the combination and the deterioration level of the water pipe, the combination having reference wave data corresponding to the wave data acquired in the information acquisition step and reference pavement information corresponding to the pavement information; The above correlations are composed of nodes in a neural network in artificial intelligence. A program for determining the degree of deterioration of water pipes.

Images