A method, device, equipment and medium for predicting the life of a water purifier filter element

Abstract

The present application discloses a method, device, equipment and medium for predicting the life of a water purifier filter cartridge, and relates to the technical field of water purifiers, and includes: obtaining filter cartridge image information, and determining the filter cartridge usage status and filter cartridge color information according to the filter cartridge image information; obtaining basic information of the water purifier, and determining a feature vector according to the filter cartridge usage status and the basic information of the water purifier; building a prediction model according to the feature vector; determining the filter cartridge performance difference based on the filter cartridge color information; and determining the filter cartridge life according to the prediction model and the filter cartridge performance difference. The present application can improve the accuracy of filter cartridge life prediction.

Description

Technical Field

[0001] The present application relates to the technical field of water purifiers, and in particular to a method, device, equipment and medium for predicting the life of a water purifier filter element. Background Art

[0002] As people become more aware of water quality, household and commercial water purifiers are becoming increasingly popular, and regular replacement of filters is the key to ensuring water quality. Traditional filter replacement relies on the manufacturer's recommended time period or the user's subjective judgment, which lacks accuracy and personalization, and is likely to cause waste of resources or water quality safety hazards.

[0003] Traditional methods for predicting the life of water purifier filter cartridges mainly rely on staff to set a fixed replacement cycle based on empirical values ​​or a simple flow counting mechanism to trigger a filter cartridge replacement reminder.

[0004] However, most traditional filter life assessment methods fail to fully utilize multi-dimensional information such as user behavior data, water quality differences, and usage frequency, resulting in low prediction accuracy. Summary of the invention

[0005] In order to improve the accuracy of filter element life prediction, the present application provides a water purifier filter element life prediction method, device, equipment and medium.

[0006] In the first aspect, the present application provides a method for predicting the life of a water purifier filter element, which adopts the following technical solution:

[0007] A method for predicting the life of a water purifier filter element, comprising:

[0008] Acquire filter element image information, and determine the filter element usage status and filter element color information according to the filter element image information;

[0009] Obtain basic information of the water purifier, and determine a feature vector according to the filter cartridge usage status and the basic information of the water purifier, wherein the feature vector includes filter cartridge usage time, total water flow through the filter cartridge, filter cartridge code, total number of filter cartridges in the water purifier, filter cartridge number, installation location, number of days each filter cartridge has been used, raw water TDS, purified water TDS, and current water production speed;

[0010] Building a prediction model based on the feature vector;

[0011] Determining filter element performance differences based on the filter element color information;

[0012] The filter element life is determined based on the prediction model and the filter element performance difference.

[0013] By adopting the above technical solution, the filter element image information is obtained for subsequent identification of the current state of the filter element. Then, based on the filter element image information, the corresponding filter element usage state and filter element color information are determined, which helps to understand the specific situation of the filter element. After obtaining the basic information of the water purifier, based on the basic information of the water purifier and the filter element usage state, the characteristic vector is determined, that is, the reference data required for building the prediction model is determined; then, the corresponding prediction model is built according to the characteristic vector; then, the filter element color information is analyzed and identified to determine the difference in filter element performance, thereby avoiding the risk of misjudgment caused by relying solely on a single indicator; after determining the difference in filter element performance, the filter element life is determined based on the prediction model and the difference in filter element performance, thereby improving the accuracy of filter element life prediction.

[0014] In a possible implementation, determining the filter element usage status and filter element color information according to the filter element image information includes:

[0015] Preprocessing the filter element image information to obtain first image information;

[0016] Performing grayscale processing on the first image information to determine second image information;

[0017] Determining the appearance of the filter element based on the second image information;

[0018] Determining filter element color information according to the first image information;

[0019] The usage status of the filter element is determined based on the filter element color information and the filter element appearance.

[0020] In a possible implementation, the step of building a prediction model according to the feature vector further includes:

[0021] Get historical usage data information;

[0022] Determining a reference feature vector according to the historical usage data information;

[0023] determining a degree of coincidence between the feature vector and the reference feature vector;

[0024] If the degree of overlap is less than or equal to a preset degree of overlap, a feature vector calibration scheme is generated.

[0025] In a possible implementation, building a prediction model according to the feature vector includes:

[0026] Preprocessing the feature vector to obtain a standard feature vector;

[0027] Get the prediction target;

[0028] Establishing a training model according to the prediction target and the standard feature vector;

[0029] The training model is calibrated to obtain the prediction model.

[0030] In a possible implementation, determining the filter element performance difference based on the filter element color information includes:

[0031] Determining the color distribution and the color change information of the filter element according to the filter element color information;

[0032] Determining a color change curve graph based on the color change information of the filter element;

[0033] According to the color distribution, determining distribution uniformity and abnormal color areas;

[0034] If the color change curve is inconsistent with the preset color change curve, determining uniformity difference information between the distribution uniformity and the preset distribution uniformity;

[0035] If the uniformity difference information is greater than the preset uniformity difference information, determining the cause of the filter element abnormality according to the abnormal color area;

[0036] According to the cause of the filter element abnormality, the performance difference of the filter element is determined.

[0037] In a possible implementation, determining the filter element life according to the prediction model and the filter element performance difference includes:

[0038] Determine the reference life value according to the performance difference of the filter element;

[0039] Determining a prediction result based on the prediction model and the life reference value;

[0040] The prediction result is matched with the filter element performance difference to determine the filter element life.

[0041] In the second aspect, the present application provides a water purifier filter life prediction device, which adopts the following technical solution:

[0042] A water purifier filter life prediction device includes: a filter image information acquisition module, a feature vector determination module, a prediction model building module, a filter performance difference determination module and a filter life determination module, wherein:

[0043] A filter element image information acquisition module is used to acquire filter element image information and determine the filter element usage status and filter element color information according to the filter element image information;

[0044] A feature vector determination module is used to obtain basic information of the water purifier, and determine a feature vector according to the use status of the filter element and the basic information of the water purifier, wherein the feature vector includes the use time of the filter element, the total water flow of the filter element, the filter element code, the total number of filter elements in the water purifier, the filter element of which level, the installation position, the number of days each filter element has been used, the raw water TDS, the purified water TDS, and the current water production speed;

[0045] A prediction model building module, used to build a prediction model according to the feature vector;

[0046] A filter element performance difference determination module, used to determine the filter element performance difference based on the filter element color information;

[0047] The filter element life determination module is used to determine the filter element life according to the prediction model and the filter element performance difference.

[0048] By adopting the above technical solution, the filter element image information acquisition module acquires the filter element image information for subsequent identification of the current state of the filter element, and then determines the corresponding filter element usage state and filter element color information based on the filter element image information, which helps to understand the specific situation of the filter element; after obtaining the basic information of the water purifier, the feature vector determination module determines the feature vector based on the basic information of the water purifier and the filter element usage state, that is, determines the reference data required for building the prediction model; then the prediction model building module builds the corresponding prediction model according to the feature vector; then the filter element performance difference determination module analyzes and identifies the filter element color information, determines the filter element performance difference, thereby avoiding the risk of misjudgment caused by relying solely on a single indicator; after determining the filter element performance difference, the filter element life determination module determines the filter element life according to the prediction model and the filter element performance difference, thereby improving the accuracy of the filter element life prediction.

[0049] In a possible implementation, the filter element image information acquisition module includes: a first image information determination unit, a second image information determination unit, a filter element appearance determination unit, a filter element color information determination unit, and a filter element use status unit, wherein:

[0050] A first image information determining unit, used for preprocessing the filter element image information to obtain first image information;

[0051] a second image information determining unit, configured to perform grayscale processing on the first image information to determine second image information;

[0052] A filter element appearance determining unit, configured to determine the filter element appearance based on the second image information;

[0053] A filter element color information determining unit, used to determine the filter element color information according to the first image information;

[0054] The filter element usage status unit is used to determine the filter element usage status based on the filter element color information and the filter element appearance.

[0055] In a possible implementation, the water purifier filter life prediction device further includes: a historical usage data information acquisition module, a reference feature vector module, a coincidence determination module, and a feature vector calibration solution generation module, wherein:

[0056] A historical usage data information acquisition module is used to acquire historical usage data information;

[0057] A reference feature vector module, used to determine a reference feature vector according to the historical usage data information;

[0058] A coincidence determination module, used to determine the coincidence between the feature vector and the reference feature vector;

[0059] The feature vector calibration scheme generating module is used to generate a feature vector calibration scheme if the overlap degree is less than or equal to a preset overlap degree.

[0060] In a possible implementation, the prediction model building module includes: a standard feature vector determination unit, a prediction target acquisition unit, a training model establishment unit and a prediction model determination unit, wherein:

[0061] A standard feature vector determination unit, used for preprocessing the feature vector to obtain a standard feature vector;

[0062] A prediction target acquisition unit, used for acquiring a prediction target;

[0063] A training model building unit, used to build a training model according to the prediction target and the standard feature vector;

[0064] The prediction model determination unit is used to calibrate the training model to obtain the prediction model.

[0065] In a possible implementation, the filter element performance difference determination module includes: a first information determination unit, a color change curve determination unit, a second information determination unit, a uniformity difference information determination unit, a filter element abnormality cause determination unit, and a filter element performance difference determination unit, wherein:

[0066] A first information determination unit, used to determine the color distribution and the filter element color change information according to the filter element color information;

[0067] A color change curve diagram determining unit, used for determining a color change curve diagram based on the color change information of the filter element;

[0068] A second information determination unit, configured to determine distribution uniformity and abnormal color areas according to the color distribution;

[0069] a uniformity difference information determining unit, configured to determine uniformity difference information between a distribution uniformity and a preset distribution uniformity if the color change curve diagram is inconsistent with a preset color change curve diagram;

[0070] A filter element abnormality cause determination unit, configured to determine a filter element abnormality cause according to the abnormal color area if the uniformity difference information is greater than a preset uniformity difference information;

[0071] The filter element performance difference determination unit is used to determine the filter element performance difference according to the cause of the filter element abnormality.

[0072] In a possible implementation, the filter element life determination module includes: a life reference value determination unit, a prediction result determination unit and a filter element life determination unit, wherein:

[0073] A life reference value determination unit, used to determine a life reference value according to the performance difference of the filter element;

[0074] A prediction result determination unit, configured to determine a prediction result based on the prediction model and the life reference value;

[0075] The filter element life determination unit is used to match the prediction result with the filter element performance difference to determine the filter element life.

[0076] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0077] An electronic device, comprising:

[0078] at least one processor;

[0079] Memory;

[0080] At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned water purifier filter life prediction method.

[0081] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0082] A computer-readable storage medium includes: a computer program that can be loaded by a processor and execute the above-mentioned water purifier filter element life prediction method.

[0083] In summary, this application includes the following beneficial technical effects:

[0084] The filter element image information is obtained for subsequent identification of the current state of the filter element. Then, based on the filter element image information, the corresponding filter element usage status and filter element color information are determined, which helps to understand the specific situation of the filter element. After obtaining the basic information of the water purifier, based on the basic information of the water purifier and the filter element usage status, the feature vector is determined, that is, the reference data required for building the prediction model is determined; then, the corresponding prediction model is built based on the feature vector; then, the filter element color information is analyzed and identified to determine the difference in filter element performance, thereby avoiding the risk of misjudgment caused by relying solely on a single indicator; after determining the difference in filter element performance, the filter element life is determined based on the prediction model and the difference in filter element performance, thereby improving the accuracy of filter element life prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] Figure 1 It is a flow chart of the method for predicting the life of the filter element of the water purifier of the present application;

[0086] Figure 2 It is a block diagram of a device for predicting the life of a filter element of a water purifier of the present application;

[0087] Figure 3 It is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0088] The following is combined with Figure 1-Figure 3 This application is described in further detail.

[0089] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0090] The embodiment of the present application provides a method for predicting the life of a water purifier filter cartridge, which is executed by an electronic device, which may be a server or a terminal device, wherein the server may be an independent physical server, or a server cluster or distributed device composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device may be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server may be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application.

[0091] Reference Figure 1The method comprises: step S101, step S102, step S103, step S104 and step S105, wherein:

[0092] Step S101, obtaining filter element image information, and determining the filter element usage status and filter element color information according to the filter element image information.

[0093] Specifically, each water purifier is equipped with a monitoring device for real-time monitoring of the filter element. When the water purifier starts working, the monitoring device will transmit the filter element image information to the electronic device; after receiving the filter element image information, the electronic device will perform image recognition on the filter element image information to determine the filter element color information and the filter element usage status corresponding to each filter element image information.

[0094] Step S102: Obtain basic information of the water purifier, and determine a feature vector according to the usage status of the filter element and the basic information of the water purifier.

[0095] In this embodiment of the present application, the feature vector includes the filter element usage time, the total water flow through the filter element, the filter element code, the total number of filter elements in the water purifier, the filter element of which stage, the installation location, the number of days each filter element has been used, the raw water TDS, the purified water TDS and the current water production speed.

[0096] Specifically, the staff transmits the product manual, equipment label or nameplate of the water purifier to the electronic device, and after receiving the product manual, equipment label or nameplate of the water purifier, the electronic device sets it as the basic information of the water purifier; the electronic device matches the filter element usage status and the basic information of the water purifier with the historical factors affecting the calculation of the filter element life, and sets the influencing factors of the filter element usage status and the basic information of the water purifier that are successfully matched as feature vectors.

[0097] Step S103: Build a prediction model based on the feature vector.

[0098] Specifically, after determining the feature vector, the electronic device preprocesses the feature vector and cleans the data contained in the feature vector. The electronic device checks whether there are erroneous values ​​in the data set, and processes the data that obviously does not conform to the actual logic, such as negative filter usage time and blank data or repeated values ​​of certain feature vectors. Then the electronic device builds a prediction model based on the preprocessed feature vector.

[0099] Step S104: Determine the filter element performance difference based on the filter element color information.

[0100] Specifically, after determining the filter element color information, the electronic device determines the color distribution and color change of the filter element by performing color analysis on the filter element color information; then, the electronic device judges the performance of the filter element and a new filter element based on the color distribution and color change of each filter element, and determines the performance difference of the filter element corresponding to the filter element.

[0101] Step S105: Determine the baseline life of the filter element according to the prediction model and the performance difference of the filter element.

[0102] In the embodiment of the present application, the life reference value includes the water production speed (X_V) and the purified water TDS (X_TDS) of a brand new filter element, and the water production speed (C_V) and the purified water TDS (C_TDS) of a replaced filter element.

[0103] Specifically, the electronic device determines the life reference value through a large number of tests based on the performance difference of the filter element. The electronic device uses distilled water and salt to prepare test water with a specific TDS, assuming that the TDS is (Y_TDS); then the electronic device tests the water production speed (X_V) and the purified water TDS of the new filter element as (X_TDS); at the same time, the electronic device tests the water production speed (C_V) and the purified water TDS of the replaced filter element as (C_TDS). Finally, the electronic device adjusts and corrects the prediction model according to the life reference value and calculates the filter element life.

[0104] The embodiment of the present application provides a method for predicting the life of a water purifier filter element, which obtains filter element image information for subsequent identification of the current state of the filter element, and then determines the corresponding filter element usage state and filter element color information based on the filter element image information, which helps to understand the specific situation of the filter element; after obtaining the basic information of the water purifier, based on the basic information of the water purifier and the filter element usage state, a feature vector is determined, that is, the reference data required for building a prediction model is determined; then a corresponding prediction model is built based on the feature vector; then the filter element color information is analyzed and identified to determine the filter element performance difference, thereby avoiding the risk of misjudgment caused by relying solely on a single indicator; after determining the filter element performance difference, the filter element life is determined based on the prediction model and the filter element performance difference, thereby improving the accuracy of the filter element life prediction.

[0105] According to the filter element image information, the use status of the filter element and the color information of the filter element are determined, including: preprocessing the filter element image information to obtain first image information; gray-scaling the first image information to determine second image information; based on the second image information, determining the appearance of the filter element; according to the first image information, determining the color information of the filter element; based on the filter element color information and the appearance of the filter element, determining the use status of the filter element.

[0106] Specifically, after receiving the filter element image information, the electronic device then performs a series of denoising and image enhancement preprocessing on the filter element image information, thereby improving the clarity and cleanliness of the filter element image information, and the electronic device sets the preprocessed filter element image information as the first image information; then the electronic device converts the first image information into a grayscale image and sets it as the second image information; the electronic device uses an edge detection algorithm to extract the appearance of the filter element in the second image information; at the same time, the electronic device extracts and analyzes the color features of the first image information to determine the corresponding filter element color information.

[0107] Furthermore, the electronic device analyzes the appearance of the filter element. If the edge detection shows that the filter element has obvious damage or cracks, or the morphological analysis shows that its shape is seriously deformed, this means that the physical structure of the filter element is damaged and the filtering function may be seriously affected. It can be determined that the filter element is in an abnormal state of use and needs to be replaced or repaired in time. If it is observed that the pores and other structures of the filter element in the image are seriously blocked, such as the originally clear pores are largely blocked (the visibility of the pores can be determined by analyzing the edge image or the processed binary image), it indicates that the filtration efficiency of the filter element may be reduced and it is close to the replacement stage. At the same time, the electronic device combines the color and appearance information of the filter element to evaluate the use status of the filter element.

[0108] According to the feature vector, a prediction model is built, which also includes: obtaining historical usage data information; determining a reference feature vector according to the historical usage data information; determining the overlap between the feature vector and the reference feature vector; if the overlap is less than or equal to a preset overlap, generating a feature vector calibration plan.

[0109] Specifically, after receiving the historical usage data transmitted by the monitoring device, the electronic device analyzes and processes the historical usage data to determine a reference feature vector that meets the staff's requirements; the electronic device then matches the feature vector with the reference feature vector and calculates the degree of overlap between the feature vector and the reference feature vector; the electronic device matches the degree of overlap with the preset degree of overlap. If the degree of overlap is less than or equal to the preset degree of overlap, it means that the feature vector contains inaccurate data at this time. If the feature vector is used to build a prediction model, it will lead to inaccurate prediction model building. The electronic device then backtracks the feature vector, finds out the feature vectors that do not meet the standards, eliminates them and reselects them, and generates a corresponding feature vector calibration plan.

[0110] According to the feature vector, a prediction model is built, including: preprocessing the feature vector to obtain a standard feature vector; obtaining a prediction target; building a training model according to the prediction target and the standard feature vector; and calibrating the training model to obtain a prediction model.

[0111] Specifically, after preprocessing the feature vector by cleaning and standardizing it, the electronic device sets the preprocessed feature vector as the standard feature vector; then, after receiving the predicted target worn by the staff, the electronic device uses a machine learning algorithm, such as a random forest and a support vector machine, to build a training model; the electronic device tests and calibrates the test model by using cross-validation and actual usage data, and sets the tested training model as the prediction model.

[0112] Based on the filter element color information, the filter element performance difference is determined, including: according to the filter element color information, the color distribution and the filter element color change information are determined; based on the filter element color change information, the color change curve is determined; according to the color distribution, the distribution uniformity and the abnormal color area are determined; if the color change curve is inconsistent with the preset color change curve, the uniformity difference information between the distribution uniformity and the preset distribution uniformity is determined; if the uniformity difference information is greater than the preset uniformity difference information, the cause of the filter element abnormality is determined according to the abnormal color area; according to the cause of the filter element abnormality, the filter element performance difference is determined.

[0113] Specifically, the electronic device divides the filter element color information into color intervals, counts the proportion of each color area in the filter element color information, and determines the color distribution corresponding to the filter element color information; because the electronic device stores the filter element color information in categories according to time, the electronic device analyzes the filter element color information of different time periods to determine the filter element color change information; then, the electronic device arranges the obtained filter element color change information in chronological order and draws a color change curve graph; the electronic device uses the color variance calculation method to calculate the corresponding distribution uniformity under the current color distribution situation, and at the same time, the electronic device analyzes the color proportion threshold in the color distribution situation to determine the abnormal color area.

[0114] Furthermore, the electronic device compares the color change curve graph with the preset color change area graph. If the color change curve graph is inconsistent with the preset color change curve graph, it means that the filter element has suffered wear that is not caused by normal use. The electronic device then calculates the difference between the distribution uniformity and the preset distribution uniformity to determine the uniformity difference information; the electronic device then compares the uniformity difference information with the preset uniformity difference information. If the uniformity difference information is greater than the preset uniformity difference information, it means that the filter element has an obvious performance failure. The electronic device then marks the abnormal color area, and analyzes and processes the filter element color information corresponding to the abnormal color area to determine the cause of the filter element abnormality; the electronic device then determines the filter element performance difference by analyzing and processing the cause of the filter element abnormality.

[0115] Determine the filter element life according to the prediction model and the performance difference of the filter element, including: determining a life reference value according to the performance difference of the filter element; determining a prediction result based on the prediction model and the life reference value; matching the prediction result with the performance difference of the filter element to determine the filter element life.

[0116] Specifically, in the embodiments of the present application, the life reference value includes the water production rate (X_V) and the purified water TDS (X_TDS) of a brand-new filter element, the water production rate (C_V) and the purified water TDS (C_TDS) of the replaced filter element; the performance difference of the filter element includes the ratio of the water production rate of the old filter element to the new filter element: (C_V / X_V), the ratio of the desalination rate of the filter element: (100% - C_TDS / Y_TDS) / (100% - X_TDS / YTDS), and the correlation between the water production rate and the desalination rate of the filter element for the filter element life is (K: (100% - K)), where (0 < K < 1).

[0117] Specifically, the electronic device determines the life reference value through a large number of tests according to the performance difference of the filter element. The electronic device sets test water prepared by adding salt to distilled water to a specific TDS, assuming the TDS is (Y_TDS); then the electronic device tests the water production rate (X_V) and the purified water TDS (X_TDS) of a brand-new filter element; at the same time, the electronic device tests the water production rate (C_V) and the purified water TDS (C_TDS) of the replaced filter element. The electronic device adjusts and corrects the prediction model according to the life reference value to obtain the corresponding prediction result; the electronic device matches the prediction result with the performance difference of the filter element. The electronic device calculates the ratio of the water production rate of the replaced filter element to the brand-new filter element: (C_V / X_V); then the electronic device calculates the ratio of the desalination rate of the replaced filter element to the brand-new filter element: (100% - C_TDS / Y_TDS) / (100% - X_TDS / YTDS); calculates the correlation between the water production rate and the desalination rate of the filter element for the filter element life as (K: (100% - K)), where (0 < K < 1); calculates the filter element life; determines the filter element life calculation formula corresponding to the filter element life, including:

[0118] Calculate the filter element life according to the following formula:

[0119]

[0120] Refer to Figure 2 , the water purifier filter element life prediction device 20 may specifically include: a filter element image information acquisition module 201, a feature vector determination module 202, a prediction model construction module 203, a filter element performance difference determination module 204, and a filter element life determination module 205, where,

[0121] The filter element image information acquisition module 201 is used to acquire the filter element image information and determine the filter element usage status and filter element color information according to the filter element image information;

[0122] The feature vector determination module 202 is used to obtain basic information of the water purifier, and determine the feature vector according to the use status of the filter element and the basic information of the water purifier. The feature vector includes the use time of the filter element, the total water flow of the filter element, the filter element code, the total number of filter elements in the water purifier, the filter element of which level, the installation position, the number of days each filter element has been used, the raw water TDS, the purified water TDS and the current water production speed;

[0123] A prediction model building module 203 is used to build a prediction model based on the feature vector;

[0124] A filter element performance difference determination module 204, for determining the filter element performance difference based on the filter element color information;

[0125] The filter element life determination module 205 is used to determine the filter element life according to the prediction model and the filter element performance difference.

[0126] In a possible implementation of the embodiment of the present application, the water purifier filter life prediction device 20 further includes: a historical usage data information acquisition module, a reference feature vector module, a coincidence determination module, and a feature vector calibration scheme generation module, wherein:

[0127] A historical usage data information acquisition module is used to acquire historical usage data information;

[0128] A reference feature vector module, used to determine a reference feature vector based on historical usage data information;

[0129] A coincidence determination module, used to determine the coincidence between the feature vector and the reference feature vector;

[0130] The feature vector calibration scheme generating module is used to generate a feature vector calibration scheme if the overlap degree is less than or equal to a preset overlap degree.

[0131] In a possible implementation of the embodiment of the present application, the prediction model building module 203 includes: a standard feature vector determination unit, a prediction target acquisition unit, a training model establishment unit and a prediction model determination unit, wherein:

[0132] A standard feature vector determination unit, used for preprocessing the feature vector to obtain a standard feature vector;

[0133] A prediction target acquisition unit, used for acquiring a prediction target;

[0134] A training model building unit, used to build a training model according to a prediction target and a standard feature vector;

[0135] The prediction model determination unit is used to calibrate the training model to obtain the prediction model.

[0136] In a possible implementation of the embodiment of the present application, the filter element performance difference determination module 204 includes: a first information determination unit, a color change curve determination unit, a second information determination unit, a uniformity difference information determination unit, a filter element abnormality cause determination unit, and a filter element performance difference determination unit, wherein:

[0137] A first information determination unit, used to determine the color distribution and the color change information of the filter element according to the color information of the filter element;

[0138] A color change curve diagram determining unit, used for determining a color change curve diagram based on the color change information of the filter element;

[0139] A second information determination unit, used to determine the distribution uniformity and the abnormal color area according to the color distribution;

[0140] a uniformity difference information determining unit, configured to determine uniformity difference information between the distribution uniformity and the preset distribution uniformity if the color change curve diagram is inconsistent with the preset color change curve diagram;

[0141] A filter element abnormality cause determination unit, used to determine the filter element abnormality cause according to the abnormal color area if the uniformity difference information is greater than the preset uniformity difference information;

[0142] The filter element performance difference determination unit is used to determine the filter element performance difference according to the cause of the filter element abnormality.

[0143] In a possible implementation of the embodiment of the present application, the filter element life determination module 205 includes: a life reference value determination unit, a prediction result determination unit and a filter element life determination unit, wherein:

[0144] A life reference value determination unit, used to determine a life reference value according to a performance difference of the filter element;

[0145] A prediction result determination unit, used to determine the prediction result based on the prediction model and the life reference value;

[0146] The filter element life determination unit is used to match the prediction results with the filter element performance differences to determine the filter element life.

[0147] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0148] The present application also introduces an electronic device from the perspective of a physical device, such as Figure 3 As shown, Figure 3 The electronic device 30 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 30 does not constitute a limitation on the embodiments of the present application.

[0149] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0150] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0151] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0152] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0153] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0154] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0155] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for predicting the life of a water purifier filter element, characterized in that: include: Acquire filter element image information, and determine the filter element usage status and filter element color information according to the filter element image information; Obtain basic information of the water purifier, and determine a feature vector according to the filter cartridge usage status and the basic information of the water purifier, wherein the feature vector includes filter cartridge usage time, total water flow through the filter cartridge, filter cartridge code, total number of filter cartridges in the water purifier, filter cartridge number, installation location, number of days each filter cartridge has been used, raw water TDS, purified water TDS, and current water production speed; Building a prediction model based on the feature vector; Determining filter element performance differences based on the filter element color information; Determining the life of the filter element according to the prediction model and the filter element performance difference; The determining of the filter element performance difference based on the filter element color information includes: Determining the color distribution and the color change information of the filter element according to the filter element color information; Determining a color change curve graph based on the color change information of the filter element; According to the color distribution, determining distribution uniformity and abnormal color areas; If the color change curve is inconsistent with the preset color change curve, determining uniformity difference information between the distribution uniformity and the preset distribution uniformity; If the uniformity difference information is greater than the preset uniformity difference information, determining the cause of the filter element abnormality according to the abnormal color area; Determining the performance difference of the filter element according to the cause of the filter element abnormality; Determining the filter element life according to the prediction model and the filter element performance difference includes: Determine the reference life value according to the performance difference of the filter element; Determining a prediction result based on the prediction model and the life reference value; The prediction result is matched with the filter element performance difference to determine the filter element life.

2. A method for predicting the life of a water purifier filter element according to claim 1, characterized in that: Determining the filter element usage status and filter element color information according to the filter element image information includes: Preprocessing the filter element image information to obtain first image information; Performing grayscale processing on the first image information to determine second image information; Determining the appearance of the filter element based on the second image information; Determining filter element color information according to the first image information; The usage status of the filter element is determined based on the filter element color information and the filter element appearance.

3. A method for predicting the life of a water purifier filter element according to claim 1, characterized in that: The step of building a prediction model according to the feature vector further includes: Get historical usage data information; Determining a reference feature vector according to the historical usage data information; determining a degree of coincidence between the feature vector and the reference feature vector; If the degree of overlap is less than or equal to a preset degree of overlap, a feature vector calibration scheme is generated.

4. A method for predicting the life of a water purifier filter element according to claim 1, characterized in that: The step of building a prediction model according to the feature vector includes: Preprocessing the feature vector to obtain a standard feature vector; Get the prediction target; Establishing a training model according to the prediction target and the standard feature vector; The training model is calibrated to obtain the prediction model.

5. A water purifier filter life prediction device, characterized in that: include: A filter element image information acquisition module is used to acquire filter element image information and determine the filter element usage status and filter element color information according to the filter element image information; A feature vector determination module is used to obtain basic information of the water purifier, and determine a feature vector according to the use status of the filter element and the basic information of the water purifier, wherein the feature vector includes the use time of the filter element, the total water flow of the filter element, the filter element code, the total number of filter elements in the water purifier, the filter element of which level, the installation position, the number of days each filter element has been used, the raw water TDS, the purified water TDS, and the current water production speed; A prediction model building module, used to build a prediction model according to the feature vector; A filter element performance difference determination module, used to determine the filter element performance difference based on the filter element color information; A filter element life determination module, used to determine the filter element life according to the prediction model and the filter element performance difference; The filter element performance difference determination module includes: a first information determination unit, a color change curve determination unit, a second information determination unit, a uniformity difference information determination unit, a filter element abnormality cause determination unit and a filter element performance difference determination unit, wherein: A first information determination unit, used to determine the color distribution and the filter element color change information according to the filter element color information; A color change curve diagram determining unit, used for determining a color change curve diagram based on the color change information of the filter element; A second information determination unit, configured to determine distribution uniformity and abnormal color areas according to the color distribution; a uniformity difference information determining unit, configured to determine uniformity difference information between a distribution uniformity and a preset distribution uniformity if the color change curve diagram is inconsistent with a preset color change curve diagram; A filter element abnormality cause determination unit, configured to determine a filter element abnormality cause according to the abnormal color area if the uniformity difference information is greater than a preset uniformity difference information; A filter element performance difference determination unit, used to determine the filter element performance difference according to the cause of the filter element abnormality; The filter element life determination module includes: a life reference value determination unit, a prediction result determination unit and a filter element life determination unit, wherein: A life reference value determination unit, used to determine a life reference value according to the performance difference of the filter element; A prediction result determination unit, configured to determine a prediction result based on the prediction model and the life reference value; The filter element life determination unit is used to match the prediction result with the filter element performance difference to determine the filter element life.

6. An electronic device, characterized in that: The electronic device includes: at least one processor; Memory; At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute a method for predicting the life of a water purifier filter cartridge as described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the method for predicting the life of a water purifier filter element according to any one of claims 1 to 4.

Images