Information processing device, information output method, and processing system

Abstract

The present invention provides an information processing device, an information output method, and a processing system that enable the output of information indicating the validity of prediction results obtained by a prediction model. [Solution] The system includes a data acquisition unit that acquires a first measurement value for a first indicator related to the water or material to be treated at each of multiple timings, and a second measurement value for a second indicator related to the water or material to be treated at each timing, and an information generation unit that generates first correspondence information showing the correspondence between the first measurement value and the second measurement value at each of the multiple timings. The data acquisition unit acquires a new first measurement value for the first indicator at a timing later than the multiple timings, and a new second measurement value for the second indicator at a later timing, or a first predicted value for the second indicator predicted for a later timing. Furthermore, the system includes an information output unit that outputs second correspondence information showing the correspondence between the acquired new first measurement value and either of the values, in association with the first correspondence information.

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, an information output method, and a processing system.

Background Art

[0002] For example, in a water purification plant, water purification equipment for removing suspended solids (SS: Suspended Solids) and the like contained in raw water such as river water and well water (hereinafter also referred to as treated water) is used. Specifically, in such water purification equipment, for example, by mixing a flocculant with the treated water, the suspended solids contained in the treated water are flocculated and removed by precipitation (see Patent Documents 1 and 2).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] Here, in the water purification equipment as described above, for example, by using various prediction models (hereinafter also simply referred to as prediction models), the injection rate of the flocculant that needs to be injected into the treated water is predicted. Therefore, in the water purification equipment as described above, for example, it is desired that an operator outputs information that can determine the validity of the prediction result by the prediction model.

Means for Solving the Problems

[0005] The information processing device in this disclosure includes a data acquisition unit that acquires, for each of a plurality of timings, a first measurement value for a first indicator relating to the water or material to be treated at each timing, and a second measurement value for a second indicator relating to the water or material to be treated at each timing; and an information generation unit that generates first correspondence information showing the correspondence between the first measurement value and the second measurement value at each of the plurality of timings. The data acquisition unit acquires a new first measurement value for the first indicator at a timing later than the plurality of timings, and a value among the new second measurement value for the second indicator at the later timing and a first predicted value for the second indicator predicted for the later timing. Furthermore, the data acquisition unit has an information output unit that outputs second correspondence information showing the correspondence between the acquired new first measurement value and either of the values, in association with the first correspondence information. [Effects of the Invention]

[0006] According to the information processing device, information output method, and processing system described herein, it becomes possible to output information indicating the validity of the prediction results obtained by the prediction model. [Brief explanation of the drawing]

[0007] [Figure 1] Figure 1 is a diagram illustrating the configuration of the processing system 100 in the first embodiment. [Figure 2] Figure 2 is a diagram illustrating the hardware configuration of the information processing device 1 in the first embodiment. [Figure 3] Figure 3 is a block diagram of the functions of the information processing device 1 in the first embodiment. [Figure 4] Figure 4 is a flowchart illustrating the information output process in the first embodiment. [Figure 5] Figure 5 is a flowchart illustrating the information output process in the first embodiment. [Figure 6] Figure 6 illustrates a specific example of water quality data 131. [Figure 7] Figure 7 illustrates a specific example of injection rate data 132. [Figure 8] Figure 8 illustrates a specific example of the first correspondence information 136. [Figure 9] Figure 9 illustrates a specific example of water quality data 131a. [Figure 10] Figure 10 illustrates a specific example of injection rate data 132a. [Figure 11] Figure 11 is a diagram illustrating a specific example of the second correspondence information 137. [Figure 12] Figure 12 illustrates the information output process in the first modified example. [Figure 13] Figure 13 illustrates the information output process in the first modified example. [Figure 14] Figure 14 illustrates the information output process in the second modified example. [Figure 15] Figure 15 illustrates the information output process in the second modified example. [Modes for carrying out the invention]

[0008] Embodiments of this disclosure will be described below with reference to the drawings. However, this description should not be interpreted as limiting, and will not limit the subject matter described in the claims. Furthermore, various changes, substitutions, and modifications can be made without departing from the spirit and scope of this disclosure. Different embodiments can also be combined as appropriate.

[0009] [Processing system 100 in the first embodiment] First, we will describe an example of the configuration of the processing system 100 in the first embodiment. Figure 1 is a diagram illustrating the configuration of the processing system 100 in the first embodiment.

[0010] The processing system 100 is, for example, a processing system composed of one or more processing facilities. Specifically, the processing system 100 is, for example, a water purification system (hereinafter also referred to as a water treatment system) composed of one or more water purification facilities. Hereinafter, the case where the processing system 100 is a water treatment system will be described. However, the processing system 100 may be, for example, a sewage treatment system (hereinafter also simply referred to as a sewage treatment system) arranged in a sewage treatment facility, a processing system (hereinafter also simply referred to as a sludge treatment system) for treating sewage sludge (hereinafter also simply referred to as sludge or treated material) generated in a sewage treatment facility, or an incineration system (hereinafter also simply referred to as an incineration system) for incinerating sewage sludge generated in a sewage treatment facility.

[0011] The processing system 100 includes, for example, an injection rate control system 10, a grit chamber 11, an intake well 12, a mixing tank 13, a floc formation tank 14, a sedimentation tank 15, a filtration tank 16, a clean water tank 17, and a distribution tank 18.

[0012] The grit chamber 11 is, for example, a tank into which the treated water taken from a river or the like first flows, and is a tank for sedimentation and removal of sediment and the like contained in the treated water.

[0013] The intake well 12 is, for example, a tank that adjusts the supply amount of the treated water supplied from the grit chamber 11 and supplies it to the mixing tank 13.

[0014] The mixing tank 13 is, for example, a tank for injecting a flocculant into the treated water supplied from the intake well 12.

[0015] The floc formation tank 14 is, for example, a tank that aggregates the suspended substances contained in the treated water supplied from the mixing tank 13 by stirring the treated water supplied from the mixing tank 13 to form flocs and form a tank.

[0016] The sedimentation tank 15 is, for example, a tank for sedimenting the flocs contained in the treated water supplied from the floc formation tank 14 and separating them from the treated water.

[0017] The filtration tank 16 is a tank that filters the water to be treated supplied from the sedimentation tank 15 by using a filter body (not shown) made of, for example, sand or gravel.

[0018] The water purification reservoir 17 is a tank that temporarily stores the water to be treated supplied from the filtration tank 16 (for example, the water to be treated after chlorine disinfection has been performed downstream of the filtration tank 16) and supplies it to the distribution reservoir 18.

[0019] The water distribution reservoir 18 temporarily stores the treated water supplied from the water purification reservoir 17 and supplies it to households, etc. (not shown).

[0020] The injection rate control system 10 is a system that controls, for example, the injection rate (hereinafter also simply referred to as the injection rate) of the coagulant injected into the water to be treated in the mixing tank 13.

[0021] Specifically, the injection rate control system 10 includes, for example, an information processing device 1, a storage tank T, a measuring device M1, a measuring device M2, and a pump P.

[0022] The measuring device M1 is, for example, a device for measuring the water quality of the water to be treated in the intake well 12. Specifically, the measuring device M1 is, for example, a turbidimeter for measuring the turbidity of the water to be treated in the intake well 12.

[0023] The measuring device M2 is, for example, a flow meter that measures the injection rate (amount supplied per unit time) of the coagulant supplied from the storage tank T to the mixing tank 13.

[0024] The information processing device 1 is, for example, a computer device having a CPU (Central Processing Unit) and memory, and performs a process to control the injection rate of the coagulant injected into the water to be treated in the mixing tank 13 (hereinafter also referred to as the injection rate control process).

[0025] Specifically, in the injection rate control process, the information processing device 1 inputs, for example, the water quality of the water to be treated measured by the measuring device M1 (for example, the turbidity of the water to be treated measured by the measuring device M1) into a prediction model to calculate a predicted value (hereinafter also referred to as the first predicted value) for the injection rate of the coagulant in the mixing tank 13. The prediction model may be, for example, a trained model (hereinafter simply referred to as the trained model). Alternatively, the prediction model may be, for example, a predetermined mathematical formula (injection rate formula). Then, the information processing device 1 controls the injection rate of the coagulant in the mixing tank 13 according to the calculated first predicted value.

[0026] Furthermore, the information processing device 1 may also perform control over the operation of each piece of equipment constituting the processing system 100. Additionally, the information processing device 1 may also perform monitoring of the operating status of each piece of equipment constituting the processing system 100. In other words, the information processing device 1 may function, for example, as a control device or monitoring device for each piece of equipment constituting the processing system 100.

[0027] Storage tank T is, for example, a tank for storing a coagulant to be injected into the water to be treated.

[0028] Pump P is, for example, a pump installed in piping (not shown) connecting the storage tank T and the mixing tank 13. Pump P then, for example, transfers the coagulant stored in the storage tank T to the mixing tank 13. The coagulant is supplied to 3. Specifically, the information processing device 1 supplies an amount of coagulant corresponding to the predicted value of the injection rate (first predicted value) predicted by the injection rate control process to the mixing tank 13 by, for example, controlling the frequency of an inverter (not shown) attached to the motor (not shown) of the pump P. The pump P may, for example, supply the coagulant to a pipe (not shown) connecting the intake well 12 and the mixing tank 13.

[0029] Furthermore, the information processing device 1 performs, for example, a process to output information indicating the validity of the first predicted value (hereinafter also referred to as the information output process).

[0030] Specifically, as part of its information output processing, the information processing device 1 acquires, for example, measured values ​​(hereinafter also referred to as first measured values) for an indicator related to the treated water at each of several past timings (hereinafter also referred to as simply several timings), and measured values ​​(hereinafter also referred to as second measured values) for other indicators related to the treated water at each timing (hereinafter also referred to as second measured values). The first indicator may be, for example, the water quality of the treated water in the intake well 12, etc. (for example, turbidity, color, water temperature, pH, alkalinity, etc. of the treated water). That is, the first measured value may be, for example, a measured value measured by measuring device M1. The second indicator may be, for example, the injection rate of the coagulant in the mixing tank 13. That is, the second measured value may be, for example, a measured value measured by measuring device M2.

[0031] The information processing device 1 then generates information (hereinafter also referred to as first correspondence information) that shows the correspondence between the first measurement and the second measurement at each of the multiple timings. The first correspondence information may be, for example, information that shows the position (coordinates) on a two-dimensional plane indicated by the combination of the first measurement and the second measurement corresponding to each of the multiple timings.

[0032] Next, the information processing device 1 obtains, for example, a measured value for the first indicator at a timing later than several timings (hereinafter also simply referred to as a later timing) (hereinafter also referred to as a new first measured value), and a first predicted value for the second indicator predicted for the later timing (the first predicted value calculated in the injection rate control process).

[0033] Subsequently, the information processing device 1 outputs information indicating the correspondence between a new first measurement value and a first predicted value (hereinafter also referred to as second correspondence information), associated with the first correspondence information. The second correspondence information may be, for example, information indicating the position (coordinates) on a two-dimensional plane represented by the combination of a new first measurement value and a first predicted value corresponding to a later timing.

[0034] In other words, the information processing device 1 in this embodiment generates, for example, first correspondence information that shows the trend of the correspondence between the first measured value and the second measured value at each of a plurality of timings. The information processing device 1 in this embodiment then outputs, for example, information showing the correspondence between a new first measured value and a first predicted value at a later timing, in a state that can be compared with each correspondence between the first measured value and the second measured value included in the first correspondence information.

[0035] As a result, the operator of the processing system 100 (hereinafter also simply referred to as the operator) can, for example, judge the validity of the first predicted value calculated in the injection rate control process by viewing the information output by the information processing device 1. Therefore, the operator can, for example, decide whether or not to operate the processing system 100 according to the first predicted value calculated in the injection rate control process.

[0036] In the example above, we have described the case where the first indicator is the water quality of the treated water in the intake well 12, etc., and the second indicator is the injection rate of the coagulant in the mixing tank 13, but this is not limited to this case. Specifically, the second indicator may be, for example, other water quality of the treated water in the intake well 12, etc. ( The second indicator may be a different indicator from the first indicator. The first indicator may be, for example, the injection rate of the coagulant in the mixing tank 13, and the second indicator may be, for example, the water quality of the treated water in the intake well 12, etc.

[0037] [Hardware configuration of information processing device 1] Next, the hardware configuration of the information processing device 1 will be described. Figure 2 is a diagram illustrating the hardware configuration of the information processing device 1 in the first embodiment.

[0038] As shown in Figure 2, the information processing device 1 includes a processor (CPU 101), a memory 102, a communication device 103, a storage medium 104, and an output device 105. Each part is connected to the others via a bus 106.

[0039] The storage medium 104 has, for example, a program storage area (not shown) for storing a program 110 for performing injection rate control processing and information output processing (hereinafter collectively referred to as injection rate control processing, etc.). The storage medium 104 also has, for example, a storage unit 130 (hereinafter also referred to as information storage area 130) for storing information used when performing injection rate control processing, etc. The storage medium 104 may be, for example, an HDD (Hard Disk Drive) or an SSD (Solid State Drive).

[0040] The CPU 101 performs injection rate control processing, for example, by executing a program 110 loaded into memory 102 from storage medium 104.

[0041] The communication device 103 accesses, for example, an operating terminal (not shown) where the operator inputs necessary information via a network (not shown), such as the Internet.

[0042] The output device 105 is, for example, a monitor, and outputs the processing results, such as the injection rate control processing performed by the CPU 101.

[0043] Furthermore, the electronic circuitry of the information processing device 1 may be, for example, an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). In this case, the injection rate control processing, etc., may be executed in the FPGA or ASIC.

[0044] Furthermore, the following description will assume that the processing system 100 has one information processing device 1, but it is not limited to this. Specifically, the processing system 100 may have, for example, multiple information processing devices 1. The injection rate control processing, etc., may be performed in a distributed manner across two or more information processing devices 1 included in the multiple information processing devices 1. Specifically, the injection rate control processing and the information output processing may each be performed in different information processing devices 1, for example.

[0045] [Functions of Information Processing Device 1] Next, the functions of the information processing device 1 will be described. Figure 3 is a block diagram of the functions of the information processing device 1 in the first embodiment. Specifically, Figure 3 is a block diagram of the functions that realize information output processing.

[0046] As shown in Figure 3, the information processing device 1 implements various functions, including a first data acquisition unit 111, a first information generation unit 112, a second data acquisition unit 113, a second information generation unit 114, and an information output unit 115, through the organic cooperation of hardware such as the CPU 101 and memory 102 and a program. The following describes the first data acquisition unit 111 and the second data acquisition unit 112. The unit 113 and the other unit are collectively referred to simply as the data acquisition unit. Also, the first information generation unit 112 and the second information generation unit 114 are collectively referred to simply as the information generation unit.

[0047] Furthermore, as shown in Figure 3, the information processing device 1 stores, for example, water quality data 131, injection rate data 132, other water quality data 133 (hereinafter also simply referred to as water quality data 133), frequency information 134, statistical information 135, first correspondence information 136, second correspondence information 137, and the learning model MD in the information storage area 130. The water quality data 133 and statistical information 135 will be described later.

[0048] The first data acquisition unit 111 acquires water quality data 131 measured by the measuring device M1 at each of multiple timings (multiple past timings). The water quality data 131 is, for example, data showing the measured value of the turbidity of the water to be treated. The first data acquisition unit 111 may also acquire the measured water quality data 131 each time the measuring device M1 measures the water quality data 131.

[0049] Furthermore, the first data acquisition unit 111 acquires, for example, the injection rate data 132 measured by the measuring device M2 at each of multiple timings. The injection rate data 132 is, for example, data indicating the measured value of the injection rate of the coagulant into the water to be treated. The first data acquisition unit 111 may also acquire the measured injection rate data 132 each time the measuring device M2 measures the injection rate data 132.

[0050] The first information generation unit 112 generates, for example, first correspondence information 136 that shows the correspondence between water quality data 131 and injection rate data 132 at each of multiple timings.

[0051] Specifically, the first information generation unit 112 identifies multiple coordinates (hereinafter also simply referred to as multiple coordinates) on a two-dimensional plane where the horizontal axis corresponds to the value of the water quality data 131 and the vertical axis corresponds to the value of the injection rate data 132, for example, where the combination of water quality data 131 and injection rate data 132 corresponding to each of multiple timings is located. The first information generation unit 112 then generates information indicating the identified multiple coordinates as first correspondence information 136.

[0052] Subsequently, the first information generation unit 112 generates a two-dimensional graph G1 on a two-dimensional plane in which, for example, the horizontal axis corresponds to the values ​​of the water quality data 131 and the vertical axis corresponds to the values ​​of the injection rate data 132, plotting points corresponding to each of the multiple coordinates indicated by the first correspondence information 136.

[0053] Furthermore, the first information generation unit 112, for example, assigns each of the multiple coordinates indicated by the first correspondence information 136 to multiple groups, each corresponding to a range of values ​​for the water quality data 131 and each corresponding to a range of values ​​for the injection rate data 132. Then, for example, the first information generation unit 112 generates frequency information 134 for each of the multiple groups, indicating how often the coordinates were assigned to each group. In other words, in this case, the first information generation unit 112 generates the frequency information 134 as the first correspondence information 136 (at least a part of the first correspondence information 136). Furthermore, the first information generation unit 112 generates a two-dimensional graph G2 by associating the frequency information 134 for each of the multiple groups with the corresponding positions on a two-dimensional plane, where the horizontal axis corresponds to the values ​​of the water quality data 131 and the vertical axis corresponds to the values ​​of the injection rate data 132.

[0054] The second data acquisition unit 113 acquires, for example, water quality data 131 (hereinafter also referred to as water quality data 131a) measured by the measuring device M1 at a later timing (a timing later than multiple timings).

[0055] Specifically, the second data acquisition unit 113, for example, receives the first pair of data from the first information generation unit 112. Water quality data 131a measured at the time after response information 136 is generated is obtained.

[0056] Furthermore, the second data acquisition unit 113 acquires, for example, the predicted value of the injection rate data 132 at a later time, which is predicted by the learning model MD (hereinafter also referred to as injection rate data 132a). The learning model MD is a learning model generated by learning from multiple training data (not shown) which each include at least the water quality data 131 and the injection rate data 132 measured at the same time. Specifically, the second data acquisition unit 113 acquires, for example, the injection rate data 132a indicated by the value output from the learning model MD in response to the input of data which includes at least the water quality data 131a.

[0057] The second information generation unit 114 generates, for example, second correspondence information 137 that shows the correspondence between the water quality data 131a and the injection rate data 132a acquired by the second data acquisition unit 113.

[0058] Specifically, the second information generation unit 114 identifies the coordinates (hereinafter also referred to as specific coordinates) on a two-dimensional plane where the horizontal axis corresponds to the value of the water quality data 131 and the vertical axis corresponds to the value of the injection rate data 132, where the combination of water quality data 131a and injection rate data 132a corresponding to a later timing is located. The first information generation unit 112 then generates information indicating the specific coordinates as the second correspondence information 137.

[0059] Subsequently, the second information generation unit 114 generates a two-dimensional graph G3 that highlights, for example, a position containing specific coordinates in the two-dimensional graph G1 or the two-dimensional graph G2.

[0060] The information output unit 115 outputs, for example, the first corresponding information 136 generated by the first information generation unit 112 and the second corresponding information 137 generated by the second information generation unit 114, in association with each other, to an output device 105 or a terminal device (not shown) that can access the information processing device 1.

[0061] Specifically, the information output unit 115 outputs, for example, the two-dimensional graph G3 generated by the second information generation unit 114.

[0062] [Information output processing in the first embodiment] Next, the information output process in the first embodiment will be described. Figures 4 and 5 are flowcharts illustrating the information output process in the first embodiment. Figures 6 to 11 are diagrams illustrating the information output process in the first embodiment.

[0063] The first data acquisition unit 111 acquires, for example, water quality data 131 measured by the measuring device M1 at each of multiple timings (multiple past timings) (step S1 in Figure 4).

[0064] Specifically, the first data acquisition unit 111 performs step S1, for example, at a timing specified by the operator. A specific example of water quality data 131 will be described below.

[0065] [Specific example of water quality data 131] Figure 6 illustrates a specific example of water quality data 131. The following explanation focuses on the case where water quality data 131 represents the turbidity of the treated water.

[0066] The water quality data 131 shown in Figure 6 includes, for example, a "measurement time" which sets the measurement time by the measuring device M1, and a "turbidity" which sets the turbidity measured at each measurement time.

[0067] Specifically, in the water quality data 131 shown in Figure 6, the first row of data includes, for example, "8 / 25 12:00" as the "measurement time" and "10 (degrees)" as the "turbidity".

[0068] Furthermore, in the water quality data 131 shown in Figure 6, the data in the second row includes, for example, "8 / 25 12:10" as the "measurement time" and "16 (degrees)" as the "turbidity". Explanation of the other data included in Figure 6 is omitted.

[0069] Returning to Figure 4, the first data acquisition unit 111 acquires, for example, injection rate data 132 measured by the measuring device M2 at each of multiple timings (step S2 in Figure 4). A specific example of the injection rate data 132 will be described below.

[0070] [Specific example of injection rate data 132] Figure 7 illustrates a specific example of injection rate data 132.

[0071] The injection rate data 132 shown in Figure 7 includes, for example, a "measurement time" which sets the measurement time by the measuring device M2, and an "injection rate" which sets the injection rate measured at each measurement time.

[0072] Specifically, in the injection rate data 132 shown in Figure 7, the first row of data has, for example, "8 / 25 12:00" set as the "measurement time" and "60 (mg / L)" set as the "injection rate".

[0073] Furthermore, in the injection rate data 132 shown in Figure 7, the data in the second row includes, for example, "8 / 25 12:10" as the "measurement time" and "80 (mg / L)" as the "injection rate". Explanation of the other data included in Figure 7 is omitted.

[0074] Returning to Figure 4, the first information generation unit 112 generates, for example, first correspondence information 136 that shows the correspondence between water quality data 131 and injection rate data 132 at each of multiple timings (step S3 in Figure 4). A specific example of the first correspondence information 136 will be described below.

[0075] [Specific examples of the first correspondence information 136] Figure 8 illustrates a specific example of the first correspondence information 136. Specifically, Figure 8 illustrates a specific example of a two-dimensional graph G2 generated using the first correspondence information 136. In the two-dimensional graph G2 shown in Figure 8, the horizontal axis corresponds to the value of the water quality data 131 (data indicating turbidity), and the vertical axis corresponds to the value of the injection rate data 132.

[0076] Specifically, for example, if the percentage (frequency information 134) of coordinates where the value of water quality data 131 is 0 (degrees) or greater but less than 10 (degrees), and the value of injection rate data 132 is 20 (mg / L) or greater but less than 30 (mg / L), then the first information generation unit 112 sets "31" in the section (the section in the first column from the left and the third row from the bottom in Figure 8) that corresponds to the values ​​of water quality data 131 being 0 (degrees) or greater but less than 10 (degrees), and the values ​​of injection rate data 132 being 20 (mg / L) or greater but less than 30 (mg / L), as shown in Figure 8.

[0077] Furthermore, for example, if the proportion (frequency information 134) of coordinates where the value of water quality data 131 is 0 (degrees) or greater and less than 10 (degrees), and the value of injection rate data 132 is 30 (mg / L) or greater and less than 40 (mg / L), then the first information generation unit 112, as shown in Figure 8, will determine the coordinates where the value of water quality data 131 is 0 (degrees) or greater and less than 10 (degrees), and where the value of injection rate data 132 is 30 (mg / L) or greater and less than 40 (mg / L). Set "44" in the section corresponding to less than / L (the section that is the first column from the left and the fourth row from the bottom in Figure 8).

[0078] Furthermore, for example, if the percentage (frequency information 134) of coordinates where the value of water quality data 131 is 0 (degrees) or greater but less than 10 (degrees), and the value of injection rate data 132 is 40 (mg / L) or greater but less than 50 (mg / L), then the first information generation unit 112 sets "25" in the section (the section in the first column from the left and the fifth row from the bottom in Figure 8) that corresponds to the values ​​of water quality data 131 being 0 (degrees) or greater but less than 10 (degrees), and the values ​​of injection rate data 132 being 40 (mg / L) or greater but less than 50 (mg / L), as shown in Figure 8.

[0079] Furthermore, for example, if the percentage (frequency information 134) of coordinates where the value of water quality data 131 is 10 (degrees) or higher but less than 20 (degrees), and the value of injection rate data 132 is 20 (mg / L) or higher but less than 30 (mg / L), then the first information generation unit 112 sets "9" in the section (the section in the second column from the left and the third row from the bottom in Figure 8) that corresponds to the values ​​of water quality data 131 being 10 (degrees) or higher but less than 20 (degrees), and the values ​​of injection rate data 132 being 20 (mg / L) or higher but less than 30 (mg / L), as shown in Figure 8.

[0080] Furthermore, for example, if the percentage (frequency information 134) of coordinates where the value of water quality data 131 is 10 degrees or more and less than 20 degrees, and the value of injection rate data 132 is 30 mg / L or more and less than 40 mg / L, then the first information generation unit 112 sets "31" in the section (the section in the second column from the left and the fourth row from the bottom in Figure 8) that corresponds to the values ​​of water quality data 131 being 10 degrees or more and less than 20 degrees, and the values ​​of injection rate data 132 being 30 mg / L or more and less than 40 mg / L.

[0081] Furthermore, for example, if the percentage (frequency information 134) of coordinates where the value of water quality data 131 is 10 degrees or more and less than 20 degrees, and the value of injection rate data 132 is 40 mg / L or more and less than 50 mg / L, then the first information generation unit 112 sets "38" in the section (the section in the second column from the left and the fifth row from the bottom in Figure 8) that corresponds to the values ​​of water quality data 131 being 10 degrees or more and less than 20 degrees, and the values ​​of injection rate data 132 being 40 mg / L or more and less than 50 mg / L.

[0082] Furthermore, for example, if the percentage (frequency information 134) of coordinates where the value of water quality data 131 is 10 degrees or more and less than 20 degrees, and the value of injection rate data 132 is 50 mg / L or more and less than 60 mg / L, then the first information generation unit 112 sets "22" in the section (the section in the second column from the left and the sixth row from the bottom in Figure 8) that corresponds to the values ​​of water quality data 131 being 10 degrees or more and less than 20 degrees, and the values ​​of injection rate data 132 being 50 mg / L or more and less than 60 mg / L. Explanation of other information included in Figure 8 is omitted.

[0083] Returning to Figure 5, the second data acquisition unit 113 acquires, for example, water quality data 131a measured by the measuring device M1 at a later time (step S11 in Figure 5).

[0084] Specifically, the second data acquisition unit 113 performs step S11, for example, at a timing specified by the operator after step S3 in Figure 4 has been performed. A specific example of water quality data 131a will be described below.

[0085] [Specific example of water quality data 131a] Figure 9 illustrates a specific example of water quality data 131a. The water quality data 131a shown in Figure 9 has the same items as, for example, the water quality data 131 described in Figure 6.

[0086] Specifically, in the water quality data 131a shown in Figure 9, for example, "11 / 07 12:00" is set as the "measurement time" and "28 (degrees)" is set as the "turbidity".

[0087] Returning to Figure 5, the second data acquisition unit 113 acquires, for example, injection rate data 132a at a later timing (predicted value for the injection rate of the coagulant at a later timing) (step S12 in Figure 5).

[0088] Specifically, the second data acquisition unit 113 acquires injection rate data 132a at a later time point by using a learning model MD generated by learning training data that includes at least water quality data 131 and injection rate data 132 measured at the same time point.

[0089] More specifically, the second data acquisition unit 113 acquires the values ​​output from the learning model MD as injection rate data 132a at a later time by inputting data that includes at least the water quality data 131a acquired in step S11.

[0090] The training data used to generate the learning model MD may include, for example, water quality data 131 and injection rate data 132 measured at the same time, as well as other data measured at the same time as the water quality data 131 and injection rate data 132 (for example, other water quality data such as the chromaticity, temperature, pH, and alkalinity of the treated water). In this case, the second data acquisition unit 113 may, for example, acquire the value output from the learning model MD as injection rate data 132a at a later time by inputting the water quality data 131a acquired in step S11 and other data measured at the same time as the water quality data 131a. A specific example of the injection rate data 132a will be described below.

[0091] [Specific example of injection rate data 132a] Figure 10 illustrates a specific example of injection rate data 132a.

[0092] The injection rate data 132a shown in Figure 10 includes, for example, a "predicted time" where the prediction time by the learning model MD is set, and an "injection rate (predicted value)" where the predicted value for the injection rate of the flocculant at each predicted time is set.

[0093] Specifically, in the injection rate data 132a shown in Figure 10, for example, "11 / 07 12:00" is set as the "predicted time" and "55 (mg / L)" is set as the "injection rate (predicted value)".

[0094] Returning to Figure 5, the second information generation unit 114 generates, for example, second correspondence information 137 that shows the correspondence between the water quality data 131a acquired in step S11 and the injection rate data 132a acquired in step S12 (step S13 in Figure 5). A specific example of the second correspondence information 137 will be described below.

[0095] [Specific examples of information 137 in the second correspondence information] Figure 11 is a diagram illustrating a specific example of the second correspondence information 137. Specifically, Figure 11 shows a specific example of a two-dimensional graph G3 generated by using the second correspondence information 137. This is a diagram for explanation. More specifically, Figure 11 shows the case where the section containing the coordinates (specific coordinates) indicated by the second correspondence information 137 is highlighted among the sections included in the two-dimensional graph G2 explained in Figure 8.

[0096] Specifically, the water quality data 131a shown in Figure 9 is 20°C or higher and less than 30°C. Also, the injection rate data 132a shown in Figure 10 is 50 mg / L or higher and less than 60 mg / L. Therefore, as shown in Figure 11, the second information generation unit 114 highlights the section (the third column from the left and the sixth row from the bottom in Figure 11) that corresponds to the water quality data 131 value being 20°C or higher and less than 30°C, and the injection rate data 132 value being 50 mg / L or higher and less than 60 mg / L.

[0097] In this case, the second information generation unit 114 may, for example, display a symbol or figure indicating that the area containing the coordinates indicated by the second correspondence information 137 is the area containing the coordinates indicated by the second correspondence information 137. In this case, the second information generation unit 114 may, for example, set the display color of the area containing the coordinates indicated by the second correspondence information 137 to a different color from the display color of the area not containing the coordinates indicated by the second correspondence information 137.

[0098] Returning to Figure 5, the information output unit 115 outputs, for example, the first correspondence information 136 generated in step S3 and the second correspondence information 137 generated in step S13, in association with each other (step S14 in Figure 5).

[0099] Specifically, the information output unit 115 outputs, for example, the two-dimensional graph G3 described in Figure 11 to the output device 105, etc.

[0100] Subsequently, the operator views the two-dimensional graph G3 output to, for example, the output device 105, and if they determine that the injection rate data 132a acquired in step S12 is highly valid, they inject the coagulant into the water to be treated according to the injection rate data 132a acquired in step S12.

[0101] Specifically, for example, if the frequency information 134 set in the section corresponding to the second correspondence information 137 (highlighted section) is above a predetermined threshold, the operator may determine that the combination of water quality data 131a acquired in step S11 and injection rate data 132a acquired in step S12 is a combination that occurs frequently, and therefore determine that the injection rate data 132a acquired in step S12 is highly valid. On the other hand, for example, if the frequency information 134 set in the section corresponding to the second correspondence information 137 (highlighted section) is below a predetermined threshold, the operator may determine that the combination of water quality data 131a acquired in step S11 and injection rate data 132a acquired in step S12 is a combination that occurs infrequently, and therefore determine that the injection rate data 132a acquired in step S12 is not highly valid.

[0102] For example, if the operator determines that the injection rate data 132a obtained in step S12 is highly valid, the operator controls the injection rate (amount supplied per unit time) of the coagulant supplied from the storage tank T to the mixing tank 13 by adjusting the frequency of the inverter attached to the motor of the pump P according to the injection rate data 132a obtained in step S12, thereby controlling the system so that it approaches the injection rate data 132a obtained in step S12.

[0103] Furthermore, the information processing device 1 determines, for example, whether the frequency information 134 set in the section corresponding to the second corresponding information 137 (highlighted section) is above a predetermined threshold. The information indicating the judgment result may be output to the output device 105, etc.

[0104] As described above, the information processing device 1 in this embodiment acquires, for example, water quality data 131 for the water to be treated at each of multiple timings, and coagulant injection rate data 132 for the water to be treated at each timing. The information processing device 1 in this embodiment then generates, for example, first correspondence information 136 that shows the correspondence between the water quality data 131 and the injection rate data 132 at each of the multiple timings.

[0105] Subsequently, the information processing device 1 in this embodiment acquires, for example, water quality data 131a for the water to be treated at a timing later than the multiple timings, and predicted injection rate data 132a for a timing later than the multiple timings. Then, the information processing device 1 in this embodiment outputs, for example, second correspondence information 137 showing the correspondence between the water quality data 131a and the injection rate data 132a, in association with the first correspondence information 136.

[0106] Specifically, the information processing device 1 in this embodiment, for example, distributes each combination of water quality data 131 and injection rate data 132 corresponding to multiple timings into multiple groups, each group corresponding to a range of values ​​for the water quality data 131 and each group corresponding to a range of values ​​for the injection rate data 132. The information processing device 1 in this embodiment then generates frequency information 134 as first correspondence information 136, which indicates the frequency with which each of the multiple groups has been distributed a combination of water quality data 131 and injection rate data 132.

[0107] This allows the operator to, for example, view the information output by the information processing device 1 to determine the validity of the injection rate data 132a (predicted value of injection rate data 132) calculated in the injection rate control process. In other words, the operator can, for example, view the information output by the information processing device 1 to determine the validity of the prediction results from a prediction model whose calculation process is a black box. Therefore, the operator can, for example, view the information output by the information processing device 1 to determine whether or not to operate the processing system 100 according to the injection rate data 132a calculated in the injection rate control process.

[0108] Furthermore, operators (for example, less experienced operators) can, for instance, view the information output by the information processing device 1 and use that information as reference information when operating the processing system 100. In other words, operators can, for example, use the information output by the information processing device 1 as a tool for technical skill transfer.

[0109] In the example above, we described a case where data indicating the turbidity of the treated water is used as water quality data 131. However, water quality data 131 may also be data indicating the color, temperature, pH, alkalinity, etc., of the treated water, water quality data specified by the operator, or water quality data that can be judged to have a high contribution rate in the prediction by the learning model MD.

[0110] Furthermore, in the example above, we described the case where the injection rate data 132 is data indicating the injection rate of a coagulant into the water to be treated. However, the injection rate data 132 may also be data indicating, for example, the injection rate of chlorine or activated carbon into the water to be treated. Hereafter, coagulants, chlorine, and activated carbon will be collectively referred to simply as chemicals.

[0111] Furthermore, if the treatment system 100 is a sewage treatment system, the information processing device 1, for example, determines the ammonia concentration, nitrate concentration (nitrite concentration), BOD (Biological Oxygen Demand) concentration, COD (Chemical Oxygen Demand) concentration, and DO (Dissolved Oxygen) concentration of the water to be treated in a reaction tank (not shown) that performs biological treatment on the water to be treated supplied from the primary sedimentation tank (not shown) as a first It may be used as an indicator. In this case, the information processing device 1 may use, for example, the amount of air supplied to the reaction vessel (aeration rate) as a second indicator.

[0112] Furthermore, if the processing system 100 is an incineration system, the information processing device 1 may use, for example, the flow rate, temperature, and water content of the sludge supplied to the incinerator (not shown) that incinerates the sludge as a first indicator. In this case, the information processing device 1 may also use, for example, the amount of thermal energy recovered in a heat exchanger (not shown), which is downstream equipment of the incinerator, as a second indicator.

[0113] Furthermore, if the processing system 100 is a sludge processing system, the information processing device 1 may use, for example, the flow rate, temperature, solid content, and viscosity of the sludge supplied to the dewatering machine that dewaters the sludge as a first indicator. In this case, the information processing device 1 may also use, for example, the water content of the sludge discharged from the dewatering machine (sludge after dewatering) as a second indicator.

[0114] [Information output processing in the first modified example] Next, the information output processing in a modified version of the first embodiment (hereinafter also referred to as the first modified version) will be described. Figures 12 and 13 illustrate the information output processing in the first modified version.

[0115] In the first embodiment, the information output processing described the case in which a first correspondence information 136 is generated that associates water quality data 131 with injection rate data 132. In contrast, in the information output processing of the first modified example, statistical information 135 is generated along with the first correspondence information 136 (hereinafter also referred to as the first correspondence information 136a) that associates water quality data 131 with water quality data 133.

[0116] In other words, in the information output processing of the first modified example, unlike in the first embodiment, the first corresponding information 136a is generated by using water quality data 133 as a second indicator instead of injection rate data 132. Also, in the information output processing of the first modified example, statistical information 135 is generated by using injection rate data 132 as another indicator (hereinafter also referred to as a third indicator) that is different from the first and second indicators. The differences from the information output processing of the first embodiment will be explained below.

[0117] The first data acquisition unit 111 acquires, for example, water quality data 131 measured by the measuring device M1 at each of multiple timings (multiple past timings), and water quality data 133 measured by the measuring device M1 or another measuring device (not shown) different from the measuring device M1 at each of the multiple timings (step S1 in Figure 4). The following explanation will describe the case where the water quality data 131 is data indicating the turbidity of the water to be treated, and the water quality data 133 is data indicating the chromaticity of the water to be treated.

[0118] Furthermore, the first data acquisition unit 111 acquires, for example, injection rate data 132 measured by the measuring device M2 at each of multiple timings (step S2 in Figure 4).

[0119] The first information generation unit 112 then generates, for example, first correspondence information 136a that shows the correspondence between water quality data 131 and water quality data 133 at each of multiple timings (step S3 in Figure 4).

[0120] Specifically, the first information generation unit 112 generates, for example, a combination of water quality data 131 and water quality data 133 corresponding to each of multiple timings on a two-dimensional plane where the horizontal axis corresponds to the value of water quality data 131 and the vertical axis corresponds to the value of water quality data 133 (acquired in step S1). The first information generation unit 112 identifies multiple coordinates (multiple coordinates indicated by the first correspondence information 136a) where the combination of water quality data 131 and water quality data 133 is located. The first information generation unit 112 then assigns each of the multiple coordinates to multiple groups, which are divided according to the range of values ​​for water quality data 131 and the range of values ​​for water quality data 133. Furthermore, the first information generation unit 112 calculates statistical information 135 for each of the multiple groups, for example, the injection rate data 132 (injection rate data 132 measured at the same time as the combination of water quality data 131 and water quality data 133 corresponding to each coordinate) that is assigned to each group. The statistical information 135 is, for example, statistics such as the median, mean, maximum, 25th percentile, and 75th percentile of the injection rate data 132 that is assigned to each group that is assigned to each coordinate. Subsequently, the first information generation unit 112 generates a two-dimensional graph G2 (hereinafter also referred to as two-dimensional graph G2a) by associating statistical information 135 for each of the multiple groups with the corresponding positions on a two-dimensional plane where the horizontal axis corresponds to the values ​​of water quality data 131 and the vertical axis corresponds to the values ​​of water quality data 133.

[0121] In other words, in step S3, the first information generation unit 112 further associates, for example, the first correspondence information 136a corresponding to each of the multiple timings with the statistical information 135 corresponding to each of the multiple groups. A specific example of the first correspondence information 136a will be described below.

[0122] [Specific example of the first correspondence information 136a] Figure 12 illustrates a specific example of the first correspondence information 136a. Specifically, Figure 12 illustrates a specific example of a two-dimensional graph G2a generated by using the first correspondence information 136a. In the two-dimensional graph G2a shown in Figure 12, the horizontal axis corresponds to the value of water quality data 131 (data indicating turbidity), and the vertical axis corresponds to the value of water quality data 133 (data indicating chromaticity).

[0123] Specifically, for example, if the statistical information 135 of the injection rate data 132 corresponding to the coordinate where the value of water quality data 133 is 0 or greater but less than 5 degrees, among the coordinates where the value of water quality data 131 is 0 or greater but less than 10 degrees, then the first information generation unit 112 sets "22" in the section (the section that is the first column from the left and the first row from the bottom in Figure 12) that corresponds to the section where the value of water quality data 131 is 0 or greater but less than 10 degrees, and the value of water quality data 133 is 0 or greater but less than 5 degrees.

[0124] Furthermore, for example, if the statistical information 135 of the injection rate data 132 corresponding to the coordinate where the value of water quality data 133 is 5 degrees or more and less than 10 degrees, among the coordinates where the value of water quality data 131 is 0 degrees or more and less than 10 degrees, then the first information generation unit 112 sets "24" in the section (the section that is the first column from the left and the second row from the bottom in Figure 12) that corresponds to the section where the value of water quality data 133 is 0 degrees or more and less than 10 degrees, as shown in Figure 12.

[0125] Furthermore, for example, if the statistical information 135 of the injection rate data 132 corresponding to the coordinate where the value of water quality data 133 is 10 degrees or more but less than 15 degrees, among the coordinates where the value of water quality data 131 is 0 degrees or more but less than 10 degrees, then the first information generation unit 112 sets "24" in the section (the section that is the first column from the left and the third row from the bottom in Figure 12) that corresponds to the section where the value of water quality data 133 is 0 degrees or more but less than 10 degrees, as shown in Figure 12.

[0126] Furthermore, for example, if the statistical information 135 of the injection rate data 132 corresponding to the coordinate where the value of water quality data 133 is 15 degrees or more and less than 20 degrees, among the coordinates where the value of water quality data 131 is 0 degrees or more and less than 10 degrees, then the first information generation unit 112 sets "27" in the section (the section that is the first column from the left and the fourth row from the bottom in Figure 12) that corresponds to the section where the value of water quality data 133 is 0 degrees or more and less than 10 degrees, and also corresponds to the section where the value of water quality data 133 is 15 degrees or more and less than 20 degrees, as shown in Figure 12.

[0127] Furthermore, for example, if the statistical information 135 of the injection rate data 132 corresponding to the coordinate where the value of water quality data 133 is 20 or more but less than 25 among the coordinates where the value of water quality data 131 is 0 or more but less than 10, then the first information generation unit 112 sets "31" in the section (the section that is the first column from the left and the fifth row from the bottom in Figure 12) that corresponds to the value of water quality data 133 being 0 or more but less than 10, and also to the section where the value of water quality data 133 is 20 or more but less than 25, as shown in Figure 12. Explanation of other information included in Figure 12 is omitted.

[0128] Returning to Figure 5, the second data acquisition unit 113 acquires, for example, water quality data 131a, which is the measured value of the treated water measured by the measuring device M1 at a later time, and water quality data 133 (hereinafter also referred to as water quality data 133a), which is the measured value of the treated water measured by the measuring device M1 or another measuring device different from the measuring device M1 (not shown) at a later time (step S11 in Figure 5).

[0129] Furthermore, the second data acquisition unit 113 acquires injection rate data 132a at a later timing (a timing later than multiple timings) (step S12 in Figure 5).

[0130] Specifically, the second data acquisition unit 113 acquires injection rate data 132a at a later time by using a learning model MD generated by learning training data (not shown) which includes at least the water quality data 131, water quality data 133, and injection rate data 132 measured at the same time. Note that the learning model used in the first modified example may be a different learning model from the learning model MD used in the first embodiment.

[0131] Subsequently, the second information generation unit 114 generates, for example, second correspondence information 137 (hereinafter also referred to as second correspondence information 137a) that shows the correspondence between the water quality data 131a acquired in step S11 and the water quality data 133a acquired in step S11 (step S13 in Figure 5). A specific example of the second correspondence information 137a will be described below.

[0132] [Specific examples of the second correspondence information 137a] Figure 13 illustrates a specific example of the second correspondence information 137a. Specifically, Figure 13 illustrates a specific example of a two-dimensional graph G3 (hereinafter also referred to as two-dimensional graph G3a) generated by using the second correspondence information 137a. More specifically, Figure 13 shows the case in which a section containing the coordinates (specific coordinates) indicated by the second correspondence information 137a is highlighted among the sections included in the two-dimensional graph G2a explained in Figure 12.

[0133] Specifically, for example, if the value of water quality data 131a acquired in step S11 is 22 (degrees) and the value of water quality data 133a acquired in step S11 is 11 (degrees), the second information generation unit 114 will, as shown in Figure 13, generate a section (the third column from the left and the third row from the bottom in Figure 13) that corresponds to the value of water quality data 131 being 20 (degrees) or more and less than 30 (degrees), and the value of water quality data 133 being 10 (degrees) or more and less than 15 (degrees). Highlight the section that is the eye.

[0134] Returning to Figure 5, the information output unit 115 outputs, for example, the first correspondence information 136a generated in step S3 and the second correspondence information 137a generated in step S13 in association with each other (step S14 in Figure 5).

[0135] Specifically, the information output unit 115 outputs, for example, the two-dimensional graph G3a described in Figure 13 to the output device 105, etc.

[0136] In other words, the information output unit 115 outputs, for example, first correspondence information 136a corresponding to each of the multiple timings, statistical information 135 corresponding to each of the multiple groups, and second correspondence information 137a corresponding to a later timing, in association with each other.

[0137] In addition, the information output unit 115 may also output, for example, the injection rate data 132a acquired in step S12, in step S14.

[0138] Subsequently, the operator, for example, views the two-dimensional graph G3a output to the output device 105, and if they determine that the injection rate data 132a acquired in step S12 is highly valid, they inject the coagulant into the water to be treated according to the injection rate data 132a acquired in step S12.

[0139] Specifically, for example, the operator may determine that the validity of the injection rate data 132a obtained in step S12 is high if the difference (absolute value of the difference) between the injection rate data 132a obtained in step S12 and the statistical information 135 set in the section corresponding to the second correspondence information 137a (highlighted section) is less than a predetermined threshold. On the other hand, for example, if the difference (absolute value of the difference) between the injection rate data 132a obtained in step S12 and the statistical information 135 set in the section corresponding to the second correspondence information 137a (highlighted section) is greater than or equal to a predetermined threshold, the operator may determine that the validity of the injection rate data 132a obtained in step S12 is low.

[0140] For example, if the operator determines that the injection rate data 132a obtained in step S12 is highly valid, the operator controls the injection rate (amount supplied per unit time) of the coagulant supplied from the storage tank T to the mixing tank 13 by adjusting the frequency of the inverter attached to the motor of the pump P according to the injection rate data 132a obtained in step S12, thereby controlling the injection rate (amount supplied per unit time) of the coagulant supplied from the storage tank T to the mixing tank 13 to approach the injection rate data 132a obtained in step S12.

[0141] In this modified example, the information processing device 1 acquires, for example, water quality data 131 and water quality data 133 for the water to be treated at each of multiple timings. The information processing device 1 then generates, for example, first correspondence information 136a that shows the correspondence between the water quality data 131 and water quality data 133 at each of the multiple timings.

[0142] Subsequently, the information processing device 1 in this modified example acquires, for example, water quality data 131a for the water to be treated at a timing later than multiple timings, and water quality data 133a for the water to be treated at a timing later than multiple timings. Then, the information processing device 1 in this modified example outputs, for example, second correspondence information 137a showing the correspondence between water quality data 131a and water quality data 133a, in association with the first correspondence information 136a.

[0143] Specifically, the information processing device 1 in this modified example, for example, at multiple timing intervals, The system acquires injection rate data 132 for the water to be treated at each timing. The information processing device 1 in this modified example then distributes each of the injection rate data 132 corresponding to multiple timings into multiple groups based on the first correspondence information 136a corresponding to each timing, and generates statistical information 135 that shows the statistical values ​​of the injection rate data 132 distributed to each of the multiple groups. Furthermore, the information processing device 1 in this modified example outputs the second correspondence information 137a and the statistical information 135 corresponding to each of the multiple groups in association with the first correspondence information 136a.

[0144] As a result, the operator can, for example, view the information output by the information processing device 1, as in the first embodiment, and make a judgment regarding the validity of the injection rate data 132a (predicted value of injection rate data 132) calculated in the injection rate control process. Therefore, the operator can, for example, make a judgment regarding whether or not to operate the processing system 100 according to the injection rate data 132a calculated in the injection rate control process.

[0145] Furthermore, the information processing device 1 may, in its information output processing, generate (output) the first correspondence information 136 and the second correspondence information 137 (2D graph G3) described in the first embodiment, and the first correspondence information 136a and the second correspondence information 137a (2D graph G3a) described in the first modified example. The operator may then make a judgment regarding the validity of the injection rate data 132a acquired in step S12 by viewing the first correspondence information 136 and the second correspondence information 137 (2D graph G3) described in the first embodiment, and the first correspondence information 136a and the second correspondence information 137a (2D graph G3a) described in the first modified example.

[0146] Specifically, if the operator, for example, after viewing the two-dimensional graph G3 explained in Figure 11, determines that the frequency information 134 set in the section corresponding to the second correspondence information 137 (highlighted section) is below a predetermined threshold, the operator may further view the two-dimensional graph G3a explained in Figure 13. Then, for example, if, after further viewing the two-dimensional graph G3a, the operator determines that the difference (absolute value of the difference) between the injection rate data 132a obtained in step S12 and the statistical information 135 set in the section corresponding to the second correspondence information 137 (highlighted section) is below a predetermined threshold, the operator may determine that the injection rate data 132a obtained in step S12 is highly valid. On the other hand, for example, if, after further viewing of the two-dimensional graph G3a, the difference (absolute value of the difference) between the injection rate data 132a obtained in step S12 and the statistical information 135 set in the section corresponding to the second correspondence information 137 (highlighted section) is greater than or equal to a predetermined threshold, the operator may determine that the validity of the injection rate data 132a obtained in step S12 is low.

[0147] [Information output processing in the second modified example] Next, the information output processing in a modified version of the first embodiment (hereinafter also referred to as the second modified version) will be described. Figures 14 and 15 illustrate the information output processing in the second modified version.

[0148] In the first embodiment, the information output processing described the case in which a first correspondence information 136 is generated that associates water quality data 131 with injection rate data 132. In contrast, in the information output processing of the second modified example, a first correspondence information 136 (hereinafter also referred to as first correspondence information 136b) is generated that associates water quality data 131 with water quality data 133.

[0149] In other words, in the information output processing in the second modified example, the process is different from the case in the first embodiment. Unlike the first modified example, the first corresponding information 136b is generated by using water quality data 133 as a second indicator instead of injection rate data 132. The differences from the information output processing in the first embodiment will be explained below.

[0150] The first data acquisition unit 111 acquires, for example, water quality data 131 measured by the measuring device M1 at each of multiple timings (multiple past timings), and water quality data 133 measured by the measuring device M1 or another measuring device (not shown) different from the measuring device M1 at each of the multiple timings (step S1 in Figure 4). Note that the information processing device 1 in the second modified example may not perform step S2 in Figure 4.

[0151] The first information generation unit 112 then generates, for example, first correspondence information 136b that shows the correspondence between water quality data 131 and water quality data 133 at each of multiple timings (step S3 in Figure 4).

[0152] Specifically, the first information generation unit 112 identifies multiple coordinates (multiple coordinates indicated by the first correspondence information 136b) where combinations of water quality data 131 and water quality data 133 corresponding to each of multiple timings (combinations of water quality data 131 and water quality data 133 acquired in step S1) are located on a two-dimensional plane where the horizontal axis corresponds to the value of water quality data 131 and the vertical axis corresponds to the value of water quality data 133. Then, the first information generation unit 112 assigns each of the multiple coordinates to multiple groups, which are divided according to the range of values ​​for water quality data 131 and the range of values ​​for water quality data 133. Furthermore, the first information generation unit 112 generates frequency information 134 for each of the multiple groups, indicating the frequency with which coordinates have been assigned to each group. Subsequently, the first information generation unit 112 generates a two-dimensional graph G2 (hereinafter also referred to as two-dimensional graph G2b) by associating the frequency information 134 for each of the multiple groups with the corresponding positions for each group. The following is a description of a specific example of the first correspondence information 136b.

[0153] [Specific example of the first correspondence information 136b] Figure 14 illustrates a specific example of the first correspondence information 136b. Specifically, Figure 14 illustrates a specific example of the two-dimensional graph G2b generated by using the first correspondence information 136b. In the two-dimensional graph G2b shown in Figure 14, the horizontal axis corresponds to the value of water quality data 131 (data indicating turbidity), and the vertical axis corresponds to the value of water quality data 133 (data indicating chromaticity).

[0154] Specifically, for example, if the proportion (frequency information 134) of coordinates where the value of water quality data 133 is 0 or greater but less than 5 degrees among coordinates where the value of water quality data 131 is 0 or greater but less than 10 degrees is "5 (%)", then the first information generation unit 112 sets "5" in the section (the section that is the first column from the left and the first row from the bottom in Figure 14) that corresponds to the section where the value of water quality data 131 is 0 or greater but less than 10 degrees, and the section where the value of water quality data 133 is 0 or greater but less than 5 degrees.

[0155] Furthermore, for example, if the proportion (frequency information 134) of coordinates where the value of water quality data 133 is 5 degrees or more but less than 10 degrees, among coordinates where the value of water quality data 131 is 0 degrees or more but less than 10 degrees, then the first information generation unit 112 sets "12" in the section (the section in the first column from the left and the second row from the bottom in Figure 14) that corresponds to the values ​​of water quality data 131 being 0 degrees or more but less than 10 degrees, and the section that corresponds to the values ​​of water quality data 133 being 5 degrees or more but less than 10 degrees.

[0156] Furthermore, for example, if the proportion (frequency information 134) of coordinates where the value of water quality data 133 is 10 degrees or more but less than 15 degrees among coordinates where the value of water quality data 131 is 0 degrees or more but less than 10 degrees is "24 (%)", then the first information generation unit 112 sets "24" in the section (the section that is the first column from the left and the third row from the bottom in Figure 14) that corresponds to the section where the value of water quality data 131 is 0 degrees or more but less than 10 degrees, and the section where the value of water quality data 133 is 10 degrees or more but less than 15 degrees.

[0157] Furthermore, for example, if the proportion (frequency information 134) of coordinates where the value of water quality data 133 is 15 degrees or more but less than 20 degrees among coordinates where the value of water quality data 131 is 0 degrees or more but less than 10 degrees is "41 (%)", then the first information generation unit 112 sets "41" in the section (the section that is the first column from the left and the fourth row from the bottom in Figure 14) that corresponds to the section where the value of water quality data 131 is 0 degrees or more but less than 10 degrees, and the value of water quality data 133 is 15 degrees or more but less than 20 degrees.

[0158] Furthermore, for example, if the percentage (frequency information 134) of coordinates where the water quality data 133 value is 20 degrees or more but less than 25 degrees among coordinates where the water quality data 131 value is 0 degrees or more but less than 10 degrees is "18 (%)", then the first information generation unit 112 sets "18" in the section (the section in the first column from the left and the fifth row from the bottom in Figure 14) that corresponds to the section where the water quality data 131 value is 0 degrees or more but less than 10 degrees, and the water quality data 133 value is 20 degrees or more but less than 25 degrees.

[0159] Returning to Figure 5, the second data acquisition unit 113 acquires, for example, water quality data 131a measured by the measuring device M1 at a later timing (a timing later than multiple timings) and water quality data 133a measured by the measuring device M1 or another measuring device (not shown) different from the measuring device M1 at a later timing (step S11 in Figure 5). Note that the information processing device 1 in the second modified example may not perform step S12 in Figure 5, for example.

[0160] Subsequently, the second information generation unit 114 generates, for example, second correspondence information 137 (hereinafter also referred to as second correspondence information 137b) that shows the correspondence between the water quality data 131a acquired in step S11 and the water quality data 133a acquired in step S11 (step S13 in Figure 5). A specific example of second correspondence information 137b will be described below.

[0161] [Specific examples of the second correspondence information 137b] Figure 15 illustrates a specific example of the second correspondence information 137b. Specifically, Figure 15 illustrates a specific example of the two-dimensional graph G3 (hereinafter also referred to as the two-dimensional graph G3b) generated by using the second correspondence information 137b. More specifically, Figure 15 illustrates the case in which a section containing the coordinates (specific coordinates) indicated by the second correspondence information 137b is highlighted among the sections included in the two-dimensional graph G2b described in Figure 14.

[0162] Specifically, for example, if the value of water quality data 131a acquired in step S11 is 22 (degrees) and the value of water quality data 133a acquired in step S11 is 11 (degrees), the second information generation unit 114 will highlight the section (the third column from the left and the third row from the bottom in Figure 15) that corresponds to the value of water quality data 131 being 20 (degrees) or more and less than 30 (degrees), and the value of water quality data 133 being 10 (degrees) or more and less than 15 (degrees).

[0163] Returning to Figure 5, the information output unit 115 outputs, for example, the first correspondence information 136b generated in step S3 and the second correspondence information 137b generated in step S13 in association with each other (step S14 in Figure 5).

[0164] Specifically, the information output unit 115 outputs, for example, the two-dimensional graph G3b described in Figure 15 to the output device 105, etc.

[0165] Subsequently, the operator, for example, views the two-dimensional graph G3b output to the output device 105, and if they determine that the injection rate data 132a acquired in step S12 is highly valid, they make a judgment as to whether the combination of water quality data 131a acquired in step S11 and water quality data 133a acquired in step S11 is a combination that occurs frequently.

[0166] Specifically, for example, if the frequency information 134 set in the section corresponding to the second correspondence information 137b (highlighted section) is above a predetermined threshold, the operator may determine that the combination of water quality data 131a and water quality data 133a acquired in step S11 is a combination that occurs frequently. On the other hand, for example, if the frequency information 134 set in the section corresponding to the second correspondence information 137b (highlighted section) is below a predetermined threshold, the operator may determine that the combination of water quality data 131a and water quality data 133a acquired in step S11 is a combination that occurs infrequently.

[0167] Furthermore, the information processing device 1 may, in its information output processing, generate (output) the first correspondence information 136a and the second correspondence information 137a (2D graph G3a) described in the first modified example, and the first correspondence information 136b and the second correspondence information 137b (2D graph G3b) described in the second modified example. The operator may then, for example, make a judgment regarding the validity of the injection rate data 132a acquired in step S12 by viewing the first correspondence information 136a and the second correspondence information 137a (2D graph G3a) described in the first modified example, and the first correspondence information 136b and the second correspondence information 137b (2D graph G3b) described in the second modified example.

[0168] Specifically, if, for example, the operator views the two-dimensional graph G3a described in Figure 13 and finds that the difference (absolute value of the difference) between the injection rate data 132a obtained in step S12 and the statistical information 135 set in the section corresponding to the second correspondence information 137 (highlighted section) is greater than or equal to a predetermined threshold, the operator may then view the two-dimensional graph G3b described in Figure 15.

[0169] For example, if, after further viewing the two-dimensional graph G3b explained in Figure 15, the frequency information 134 set in the section corresponding to the second correspondence information 137b (highlighted section) is above a predetermined threshold, the operator may judge that the injection rate data 132a acquired in step S12 is highly valid. On the other hand, for example, if, after further viewing the two-dimensional graph G3b explained in Figure 15, the frequency information 134 set in the section corresponding to the second correspondence information 137b (highlighted section) is below a predetermined threshold, the operator may judge that the injection rate data 132a acquired in step S12 is not highly valid.

[0170] Furthermore, the information processing device 1 (second data acquisition unit 113) may, in step S11, acquire, for example, other water quality data (for example, data indicating alkalinity, etc.) in addition to water quality data 131a and water quality data 133a. Then, the operator can, for example, use the two-dimensional data as explained in Figure 15. Even if, after further review of rough G3b, it is determined that the injection rate data 132a obtained in step S12 is highly valid, if the values ​​of other water quality data other than water quality data 131a and water quality data 133a are not within the predetermined normal range, it may be determined that the injection rate data 132a obtained in step S12 is not highly valid.

[0171] Furthermore, the information processing device 1 may, in its information output processing, generate (output) the first correspondence information 136 and the second correspondence information 137 (2D graph G3) described in the first embodiment, and the first correspondence information 136b and the second correspondence information 137b (2D graph G3b) described in the second modified example. The operator may then make a judgment regarding the validity of the injection rate data 132a acquired in step S12 by viewing the first correspondence information 136 and the second correspondence information 137 (2D graph G3) described in the first embodiment, and the first correspondence information 136b and the second correspondence information 137b (2D graph G3b) described in the second modified example.

[0172] Specifically, if the operator, for example, views the two-dimensional graph G3 described in Figure 11 and determines that the frequency information 134 set in the section corresponding to the second corresponding information 137 (highlighted section) is below a predetermined threshold, they may then view the two-dimensional graph G3b described in Figure 15.

[0173] For example, if, after further viewing the two-dimensional graph G3b explained in Figure 15, the frequency information 134 set in the section corresponding to the second correspondence information 137b (highlighted section) is above a predetermined threshold, the operator may judge that the injection rate data 132a acquired in step S12 is highly valid. On the other hand, for example, if, after further viewing the two-dimensional graph G3b explained in Figure 15, the frequency information 134 set in the section corresponding to the second correspondence information 137b (highlighted section) is below a predetermined threshold, the operator may judge that the injection rate data 132a acquired in step S12 is not highly valid.

[0174] Furthermore, it is possible to determine that the value of the injection rate data 132a acquired in step S12 increases as the value of the water quality data 133a (data indicating chromaticity) acquired in step S11 increases. For example, even if, as a result of further viewing the two-dimensional graph G3b explained in Figure 15, the frequency information 134 set in the section corresponding to the second correspondence information 137b (highlighted section) is below a predetermined threshold, if the height of the value of the water quality data 133a (water quality data 133a included in the second correspondence information 137b) acquired in step S11 satisfies the condition (hereinafter also referred to as the first condition), and the height of the value of the injection rate data 132a acquired in step S12 satisfies the condition (hereinafter also referred to as the second condition), the operator may determine that the injection rate data 132a acquired in step S12 is highly valid. The first condition is that, for example, among the water quality data 133 included in the two-dimensional graph G3b explained in Figure 15, the value of the water quality data 133a obtained in step S11 is included in the top predetermined proportion for each water quality data 133a corresponding to the water quality data 131a (water quality data 131a included in the second corresponding information 137b) obtained in step S11. The second condition is that, for example, among the injection rate data 132 included in the two-dimensional graph G3 explained in Figure 11, the value of the injection rate data 132a obtained in step S12 is included in the top predetermined proportion for each injection rate data 132 corresponding to the water quality data 131a obtained in step S11.

[0175] Furthermore, the value of the injection rate data 132a obtained in step S12 is, for example, It is possible to determine that the value of the water quality data 133a (data indicating chromaticity) acquired in step S11 decreases as the value decreases. For example, even if, as a result of further viewing the two-dimensional graph G3b explained in Figure 15, the frequency information 134 set in the section corresponding to the second correspondence information 137b (highlighted section) is below a predetermined threshold, if the low value of the water quality data 133a (water quality data 133a included in the second correspondence information 137b) acquired in step S11 satisfies the condition (hereinafter also referred to as the third condition), and the low value of the injection rate data 132a acquired in step S12 satisfies the condition (hereinafter also referred to as the fourth condition), the operator may determine that the injection rate data 132a acquired in step S12 is highly valid. The third condition is that, for example, among the water quality data 133 included in the two-dimensional graph G3b described in Figure 15, the value of the water quality data 133a obtained in step S11 is included in a predetermined lower proportion for each water quality data 133 corresponding to the water quality data 131a (water quality data 131a included in the second corresponding information 137b) obtained in step S11. The fourth condition is that, for example, among the injection rate data 132 included in the two-dimensional graph G3 described in Figure 11, the value of the injection rate data 132a obtained in step S12 is included in a predetermined lower proportion for each injection rate data 132 corresponding to the water quality data 131a obtained in step S11.

[0176] In the example above, we described the case where water quality data 133 (water quality data 133a) is data indicating the chromaticity of the water to be treated, but this is not the only case. Specifically, water quality data 133 (water quality data 133a) may be, for example, data indicating the water temperature of the water to be treated. That is, the water quality data 133a acquired in step S11 may be, for example, data that can be judged to decrease as the value of the injection rate data 132a acquired in step S12 increases.

[0177] In this case, for example, if the operator further examines the two-dimensional graph G3b explained in Figure 15 and finds that the frequency information 134 set in the section corresponding to the second correspondence information 137b (highlighted section) is below a predetermined threshold, the operator may judge that the validity of the injection rate data 132a acquired in step S12 is high if the low value of the water quality data 133a (water quality data 133a included in the second correspondence information 137b) acquired in step S11 satisfies the condition (hereinafter also called the fifth condition), and the high value of the injection rate data 132a acquired in step S12 satisfies the condition (second condition). The fifth condition is that, for example, among the water quality data 133 included in the two-dimensional graph G3b explained in Figure 15, for each water quality data 133 corresponding to the water quality data 131a (water quality data 131a included in the second corresponding information 137b) acquired in step S11, the value of the water quality data 133a acquired in step S11 is included in a predetermined lower proportion.

[0178] Furthermore, in this case, for example, if the operator further examines the two-dimensional graph G3b explained in Figure 15 and finds that the frequency information 134 set in the section corresponding to the second correspondence information 137b (highlighted section) is below a predetermined threshold, the operator may judge that the validity of the injection rate data 132a acquired in step S12 is high if the high value of the water quality data 133a (water quality data 133a included in the second correspondence information 137b) acquired in step S11 satisfies the condition (hereinafter also called the sixth condition), and the low value of the injection rate data 132a acquired in step S12 satisfies the condition (fourth condition). The sixth condition is that, for example, among the water quality data 133 included in the two-dimensional graph G3b explained in Figure 15, the value of the water quality data 133a obtained in step S11 is included in the top predetermined proportion for each water quality data 133a corresponding to the water quality data 131a (water quality data 131a included in the second corresponding information 137b) obtained in step S11. [Explanation of symbols]

[0179] 1: Information processing device 2: Storage tank 10: Injection rate control system 11: Sedimentation basin 12: Landing well 13: Mixing pond 14: Flocculation tank 15: Sedimentation tank 16: Filtration pond 17: Water purification pond 18: Water reservoir 100: Treatment system 101: CPU 102: Memory 103: Communication device 104: Storage medium 105: Bus 111: First data acquisition unit 112: First information generation unit 113: Second data acquisition unit 114: Second information generation unit 115: Information output unit 130: Memory Unit 131: Water Quality Data 132: Injection rate data 133: Water quality data MD: Learning Model M1: Measurement Device M2: Measuring device P: Pump

Claims

1. A data acquisition unit that acquires, at multiple timing intervals, a first measurement value for a first indicator related to the water or material to be treated at each timing interval, and a second measurement value for a second indicator related to the water or material to be treated at each timing interval. The system includes an information generation unit that generates first correspondence information showing the correspondence between the first measurement value and the second measurement value at each of the aforementioned multiple timings, The data acquisition unit acquires a new first measurement value for the first indicator at a timing later than the plurality of timings, and a new second measurement value for the second indicator at the later timing, and a first predicted value for the second indicator predicted for the later timing, and further, An information processing device having an information output unit that outputs second correspondence information, which shows the correspondence between the newly acquired first measurement value and any of the above values, in association with the first correspondence information.

2. The first measurement value is a measurement value for the water quality of the treated water, The information processing apparatus according to claim 1, wherein the second measurement value is a measurement value for the injection rate of chemicals into the water to be treated.

3. The information generation unit, Each of the combinations of the first measurement value and the second measurement value corresponding to the plurality of timings is allocated to a plurality of groups, each for each range of the first measurement value and each for each range of the second measurement value. The information processing apparatus according to claim 1, which generates frequency information indicating the frequency to which the combination is assigned to each of the plurality of groups as first correspondence information.

4. The data acquisition unit acquires a third measurement value for the third indicator relating to the water to be treated or the material to be treated at each of the plurality of timings. The information generation unit, Each of the third measurement values ​​corresponding to the aforementioned multiple timings is assigned to a plurality of groups based on the first corresponding information corresponding to each timing. Statistical information is generated showing the statistical quantities of the third measured values ​​assigned to each of the aforementioned multiple groups. The information processing apparatus according to claim 1, wherein the information output unit outputs the second correspondence information and the statistical information corresponding to each of the plurality of groups in association with the first correspondence information.

5. At multiple timing intervals, a first measurement value for a first indicator related to the water or material to be treated at each timing interval, and a second measurement value for a second indicator related to the water or material to be treated at each timing interval are obtained. First correspondence information is generated that shows the correspondence between the first measurement value and the second measurement value at each of the aforementioned multiple timings. Obtain a new first measurement value for the first indicator at a timing later than the aforementioned multiple timings, and obtain either a new second measurement value for the second indicator at the later timing or a first predicted value for the second indicator predicted for the later timing. An information output method that outputs second correspondence information, which shows the correspondence between the newly acquired first measurement value and any of the aforementioned values, in association with the first correspondence information.

6. A processing system comprising a processing facility for processing water or material to be processed, and an information processing device for controlling the processing facility, The aforementioned information processing device is A data acquisition unit that acquires, at multiple timing intervals, a first measurement value for a first indicator related to the water to be treated or the material to be treated at each timing interval, and a second measurement value for a second indicator related to the water to be treated or the material to be treated at each timing interval. The system includes an information generation unit that generates first correspondence information showing the correspondence between the first measurement value and the second measurement value at each of the aforementioned multiple timings, The data acquisition unit acquires a new first measurement value for the first indicator at a timing later than the plurality of timings, and a new second measurement value for the second indicator at the later timing, and a first predicted value for the second indicator predicted for the later timing, and further, A processing system having an information output unit that outputs second correspondence information, which shows the correspondence between the newly acquired first measurement value and any of the aforementioned values, in association with the first correspondence information.

Images