Mouse metabolic monitoring data processing method and system based on multi-source information

Abstract

The present invention discloses a method and system for processing mouse metabolism monitoring data based on multi-source information, the method comprising: obtaining multiple initial sensor information of a target mouse by setting multiple sensors in the mouse activity area; encoding each of the initial sensor information based on a data encoding algorithm to obtain corresponding coded sensor information; predicting the energy consumption parameters of the target mouse based on all the coded sensor information based on a neural network algorithm; and determining the abnormal analysis results corresponding to the energy consumption parameters based on the activity type of the target mouse in a historical time period. It can be seen that the present invention can more efficiently and accurately predict and analyze the energy consumption of mice, improve the monitoring effect of mice, and provide a more accurate data basis for experimental research.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for processing mouse metabolism monitoring data based on multi-source information. Background Art

[0002] By monitoring the metabolism of mice, we can fully understand the energy consumption of mice in a specific experimental environment, which is a very important requirement for many experiments. In the prior art, when realizing metabolic monitoring of mice, it is generally achieved by simply measuring a single indicator, and does not consider using multiple sensor information to improve monitoring accuracy, so its monitoring effect is poor. It can be seen that the prior art has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a mouse metabolic monitoring data processing method and system based on multi-source information, which can more efficiently and accurately predict and analyze the energy consumption of mice, improve the monitoring effect of mice, and provide a more accurate data basis for experimental research.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a method for processing mouse metabolic monitoring data based on multi-source information, the method comprising:

[0005] By setting up multiple sensors in the mouse activity area, multiple initial sensor information of the target mouse is obtained;

[0006] Based on a data encoding algorithm, encoding each of the initial sensing information to obtain corresponding encoded sensing information;

[0007] Based on a neural network algorithm, predicting the energy expenditure parameters of the target mouse according to all the encoded sensor information;

[0008] According to the activity type of the target mouse in the historical time period, the abnormal analysis result corresponding to the energy consumption parameter is determined.

[0009] As an optional embodiment, in the first aspect of the present invention, the initial sensing information is temperature information, humidity information, carbon dioxide content, oxygen content, wheel speed, number of wheel revolutions, infrared sensing information or image information.

[0010] As an optional embodiment, in the first aspect of the present invention, the activity type is exercise activity, rest activity or eating activity.

[0011] As an optional implementation, in the first aspect of the present invention, encoding each of the initial sensing information based on a data encoding algorithm to obtain corresponding encoded sensing information includes:

[0012] For each of the initial sensor information, clean the initial sensor information according to a data cleaning rule to obtain the cleaned initial sensor information;

[0013] Determine a data encoding algorithm model corresponding to the initial sensing information according to the information type corresponding to the initial sensing information; the information type is temperature information, humidity information, carbon dioxide content, oxygen content, wheel speed, wheel revolution number, infrared sensing information or image information;

[0014] The cleaned initial sensor information is encoded according to the data encoding algorithm model to obtain corresponding encoded sensor information.

[0015] As an optional embodiment, in the first aspect of the present invention, the data encoding algorithm model includes a data normalization processing model and a data rearrangement algorithm model; the data normalization processing model is a CNN neural network, which is obtained by training a training data set including training sensor data corresponding to multiple information types and corresponding normalization parameter annotations; the data rearrangement algorithm model is an LSTM neural network model, which is obtained by training a training data set including training sensor data corresponding to multiple information types and corresponding data arrangement annotations.

[0016] As an optional implementation, in the first aspect of the present invention, encoding the cleaned initial sensor information according to the data encoding algorithm model to obtain corresponding encoded sensor information includes:

[0017] Inputting the cleaned initial sensor information into the data normalization processing model to obtain output normalized sensor information;

[0018] The normalized sensor information is input into the data rearrangement algorithm model to obtain output coded sensor information.

[0019] As an optional embodiment, in the first aspect of the present invention, the energy consumption parameter of the target mouse is predicted based on all the encoded sensor information based on the neural network algorithm, including:

[0020] Input each of the coded sensor information into a trained energy consumption prediction neural network corresponding to the corresponding information type to obtain a predicted energy consumption parameter corresponding to each of the coded sensor information; the energy consumption prediction neural network is trained by a training data set including training coded sensor information corresponding to a plurality of information types and corresponding energy consumption parameter annotations;

[0021] The weighted sum average of the predicted energy consumption parameters corresponding to all the encoded sensor information is calculated to obtain the energy consumption parameter of the target mouse.

[0022] As an optional embodiment, in the first aspect of the present invention, determining the abnormal analysis result corresponding to the energy consumption parameter according to the activity type of the target mouse in the historical time period includes:

[0023] Obtaining historical activity records corresponding to the target mouse;

[0024] According to the time period type corresponding to the most recent historical time period and the historical activity records, multiple possible activity types corresponding to the target mouse are determined; the time period types are morning, noon, evening, feeding time period or medication time period;

[0025] For each of the possible activity types, determining the energy consumption interval corresponding to the possible activity type according to the correspondence between the preset type and the consumption parameter interval;

[0026] Calculating the difference between the energy consumption parameter and the energy consumption interval to obtain the difference of the possible activity type;

[0027] Calculating the weighted sum average of the differences corresponding to all the possible activity types to obtain the abnormal parameters corresponding to the target mouse;

[0028] It is determined whether the abnormal parameter is greater than a preset parameter threshold value to obtain the abnormal analysis result corresponding to the target mouse.

[0029] A second aspect of an embodiment of the present invention discloses a mouse metabolic monitoring data processing system based on multi-source information, the system comprising:

[0030] An acquisition module, used for acquiring a plurality of initial sensing information of a target mouse through a plurality of sensors arranged in an activity area of ​​the mouse;

[0031] An encoding module, used for encoding each of the initial sensing information based on a data encoding algorithm to obtain corresponding encoded sensing information;

[0032] A prediction module, used for predicting the energy consumption parameters of the target mouse based on all the encoded sensor information based on a neural network algorithm;

[0033] The analysis module is used to determine the abnormal analysis results corresponding to the energy consumption parameters according to the activity types of the target mice in the historical time period.

[0034] As an optional embodiment, in the second aspect of the present invention, the initial sensing information is temperature information, humidity information, carbon dioxide content, oxygen content, wheel speed, number of wheel revolutions, infrared sensing information or image information.

[0035] As an optional embodiment, in the second aspect of the present invention, the activity type is exercise activity, rest activity or eating activity.

[0036] As an optional implementation, in the second aspect of the present invention, encoding each of the initial sensing information based on the data encoding algorithm to obtain corresponding encoded sensing information includes:

[0037] For each of the initial sensor information, clean the initial sensor information according to a data cleaning rule to obtain the cleaned initial sensor information;

[0038] Determine a data encoding algorithm model corresponding to the initial sensing information according to the information type corresponding to the initial sensing information; the information type is temperature information, humidity information, carbon dioxide content, oxygen content, wheel speed, wheel revolution number, infrared sensing information or image information;

[0039] The cleaned initial sensor information is encoded according to the data encoding algorithm model to obtain corresponding encoded sensor information.

[0040] As an optional embodiment, in the second aspect of the present invention, the data encoding algorithm model includes a data normalization processing model and a data rearrangement algorithm model; the data normalization processing model is a CNN neural network, which is obtained by training a training data set including training sensor data corresponding to multiple information types and corresponding normalization parameter annotations; the data rearrangement algorithm model is an LSTM neural network model, which is obtained by training a training data set including training sensor data corresponding to multiple information types and corresponding data arrangement annotations.

[0041] As an optional implementation, in the second aspect of the present invention, the encoding module encodes the cleaned initial sensor information according to the data encoding algorithm model to obtain the corresponding encoded sensor information, including:

[0042] Inputting the cleaned initial sensor information into the data normalization processing model to obtain output normalized sensor information;

[0043] The normalized sensor information is input into the data rearrangement algorithm model to obtain output coded sensor information.

[0044] As an optional embodiment, in the second aspect of the present invention, the prediction module is based on a neural network algorithm, and according to all the encoded sensor information, the specific manner of predicting the energy consumption parameters of the target mouse includes:

[0045] Input each of the coded sensor information into a trained energy consumption prediction neural network corresponding to the corresponding information type to obtain a predicted energy consumption parameter corresponding to each of the coded sensor information; the energy consumption prediction neural network is trained by a training data set including training coded sensor information corresponding to a plurality of information types and corresponding energy consumption parameter annotations;

[0046] The weighted sum average of the predicted energy consumption parameters corresponding to all the encoded sensor information is calculated to obtain the energy consumption parameter of the target mouse.

[0047] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the analysis module determines the abnormal analysis result corresponding to the energy consumption parameter according to the activity type of the target mouse in the historical time period includes:

[0048] Obtaining historical activity records corresponding to the target mouse;

[0049] According to the time period type corresponding to the most recent historical time period and the historical activity records, multiple possible activity types corresponding to the target mouse are determined; the time period types are morning, noon, evening, feeding time period or medication time period;

[0050] For each of the possible activity types, determining the energy consumption interval corresponding to the possible activity type according to the correspondence between the preset type and the consumption parameter interval;

[0051] Calculating the difference between the energy consumption parameter and the energy consumption interval to obtain the difference of the possible activity type;

[0052] Calculating the weighted sum average of the differences corresponding to all the possible activity types to obtain the abnormal parameters corresponding to the target mouse;

[0053] It is determined whether the abnormal parameter is greater than a preset parameter threshold value to obtain the abnormal analysis result corresponding to the target mouse.

[0054] The third aspect of the present invention discloses another mouse metabolism monitoring data processing system based on multi-source information, the system comprising:

[0055] A memory storing executable program code;

[0056] a processor coupled to the memory;

[0057] The processor calls the executable program code stored in the memory to execute part or all of the steps in the mouse metabolic monitoring data processing method based on multi-source information disclosed in the first aspect of the present invention.

[0058] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the mouse metabolic monitoring data processing method based on multi-source information disclosed in the first aspect of the present invention.

[0059] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0060] The present invention can obtain multiple initial sensor information of target mice based on multiple sensors set in the mouse activity area, and predict the energy consumption parameters of the target mice according to the neural network algorithm after data encoding to achieve subsequent accurate abnormality analysis, thereby being able to more efficiently and accurately predict and analyze the energy consumption of mice, improve the monitoring effect of mice, and provide a more accurate data basis for experimental research. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0062] Figure 1 It is a flow chart of a method for processing mouse metabolic monitoring data based on multi-source information disclosed in an embodiment of the present invention.

[0063] Figure 2 It is a structural schematic diagram of a mouse metabolism monitoring data processing system based on multi-source information disclosed in an embodiment of the present invention.

[0064] Figure 3 It is a structural schematic diagram of another mouse metabolism monitoring data processing system based on multi-source information disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0065] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0067] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0068] The present invention discloses a mouse metabolism monitoring data processing method and system based on multi-source information, which can predict the energy consumption parameters of the target mouse according to the neural network algorithm after data encoding based on multiple initial sensor information of the target mouse obtained by multiple sensors set in the mouse activity area, so as to realize subsequent accurate abnormal analysis, thereby being able to more efficiently and accurately predict and analyze the energy consumption of the mouse, improve the monitoring effect of the mouse, and provide a more accurate data basis for experimental research. The following are detailed descriptions.

[0069] Embodiment 1

[0070] See also Figure 1 , Figure 1 : is a flow chart of a method for processing mouse metabolic monitoring data based on multi-source information disclosed in an embodiment of the present invention. Figure 1 The described mouse metabolic monitoring data processing method based on multi-source information can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the mouse metabolic monitoring data processing method based on multi-source information may include the following operations:

[0071] 101. Multiple initial sensing information of the target mouse is obtained by setting multiple sensors in the mouse activity area.

[0072] 102. Based on a data encoding algorithm, encode each initial sensing information to obtain corresponding encoded sensing information.

[0073] 103. Based on the neural network algorithm, the energy consumption parameters of the target mice are predicted according to all the encoded sensor information.

[0074] 104. Determine the abnormal analysis results corresponding to the energy consumption parameters according to the activity types of the target mice in the historical time period.

[0075] It can be seen that the above-mentioned embodiment of the invention can obtain multiple initial sensor information of the target mouse based on multiple sensors set in the mouse activity area, and predict the energy consumption parameters of the target mouse according to the neural network algorithm after data encoding to achieve subsequent accurate abnormality analysis, thereby being able to more efficiently and accurately predict and analyze the energy consumption of the mouse, improve the monitoring effect of the mouse, and provide a more accurate data basis for experimental research.

[0076] As an optional embodiment, in the above steps, the initial sensing information is temperature information, humidity information, carbon dioxide content, oxygen content, wheel speed, number of wheel revolutions, infrared sensing information or image information.

[0077] It can be seen that through the above-mentioned optional embodiments, the content of the sensor information is clarified, which can more comprehensively characterize the activities and behaviors of mice, so as to facilitate the subsequent accurate prediction of the energy consumption parameters of the target mice, assist in achieving more efficient and accurate prediction and analysis of the energy consumption of mice, improve the monitoring effect of mice, and provide a more accurate data basis for experimental research.

[0078] As an optional embodiment, in the above steps, the activity type is exercise activity, rest activity or eating activity.

[0079] It can be seen that through the above optional embodiments, the activity type is clarified, and the activity pattern of the mouse can be more comprehensively characterized, so as to facilitate the subsequent accurate analysis of the abnormal conditions of the energy consumption parameters of the mouse, and assist in achieving more efficient and accurate prediction and analysis of the energy consumption of the mouse, thereby improving the monitoring effect of the mouse and providing a more accurate data basis for experimental research.

[0080] As an optional embodiment, in the above steps, encoding each initial sensing information based on a data encoding algorithm to obtain corresponding encoded sensing information includes:

[0081] For each piece of initial sensor information, the initial sensor information is cleaned according to a data cleaning rule to obtain the cleaned initial sensor information;

[0082] Determine a data encoding algorithm model corresponding to the initial sensing information according to the information type corresponding to the initial sensing information; optionally, the information type is temperature information, humidity information, carbon dioxide content, oxygen content, wheel speed, number of wheel revolutions, infrared sensing information or image information;

[0083] The cleaned initial sensor information is encoded according to a data encoding algorithm model to obtain corresponding encoded sensor information.

[0084] It can be seen that through the above-mentioned optional embodiments, the initial sensor information can be cleaned through the data cleaning rules and then the cleaned initial sensor can be encoded based on the data coding algorithm model corresponding to the information type to obtain the corresponding coded sensor information, so as to facilitate the subsequent accurate prediction of the energy consumption parameters of the target mice, assist in achieving more efficient and accurate prediction and analysis of the energy consumption of mice, improve the monitoring effect of mice, and provide a more accurate data basis for experimental research.

[0085] As an optional embodiment, in the above steps, the data encoding algorithm model includes a data normalization processing model and a data rearrangement algorithm model; the data normalization processing model is a CNN neural network, which is obtained by training a training data set including training sensor data corresponding to multiple information types and corresponding normalization parameter annotations; the data rearrangement algorithm model is an LSTM neural network model, which is obtained by training a training data set including training sensor data corresponding to multiple information types and corresponding data arrangement annotations.

[0086] It can be seen that through the above-mentioned optional embodiments, the details of the data coding algorithm model are clarified, and the normalization and rearrangement of the data can be realized to obtain coded sensor information with more predictive possibilities, so as to facilitate the subsequent accurate prediction of the energy consumption parameters of the target mice, and assist in achieving more efficient and accurate prediction and analysis of the energy consumption of mice, thereby improving the monitoring effect of mice and providing a more accurate data basis for experimental research.

[0087] As an optional embodiment, in the above step, encoding the cleaned initial sensor information according to the data encoding algorithm model to obtain corresponding encoded sensor information includes:

[0088] Inputting the cleaned initial sensor information into a data normalization processing model to obtain output normalized sensor information;

[0089] The normalized sensor information is input into the data rearrangement algorithm model to obtain output coded sensor information.

[0090] It can be seen that through the above-mentioned optional embodiments, it is possible to achieve normalization and rearrangement of the data, and obtain coded sensor information with more predictive possibilities, so as to facilitate the subsequent accurate prediction of the energy consumption parameters of the target mice, assist in achieving more efficient and accurate prediction and analysis of the energy consumption of mice, improve the monitoring effect of mice, and provide a more accurate data basis for experimental research.

[0091] As an optional embodiment, in the above steps, based on a neural network algorithm, according to all the encoded sensor information, predicting the energy consumption parameters of the target mouse includes:

[0092] Input each coded sensor information into a trained energy consumption prediction neural network corresponding to the corresponding information type to obtain a predicted energy consumption parameter corresponding to each coded sensor information; optionally, the energy consumption prediction neural network is trained by a training data set including training coded sensor information corresponding to a plurality of information types and corresponding energy consumption parameter annotations;

[0093] The weighted sum average of the predicted energy expenditure parameters corresponding to all encoded sensor information was calculated to obtain the energy expenditure parameters of the target mouse.

[0094] It can be seen that through the above-mentioned optional embodiments, the neural network trained by multiple different types of training data can predict the predicted energy consumption parameters corresponding to different encoded sensor information, and the most accurate energy consumption parameters of the target mice can be obtained by weighted calculation, so as to facilitate the monitoring of mouse metabolism and subsequent abnormality analysis, and assist in achieving more efficient and accurate prediction and analysis of mouse energy consumption, improve the monitoring effect of mice, and provide a more accurate data basis for experimental research.

[0095] As an optional embodiment, in the above step, determining the abnormal analysis result corresponding to the energy consumption parameter according to the activity type of the target mouse in the historical time period includes:

[0096] Obtain the historical activity records corresponding to the target mouse;

[0097] According to the time period type corresponding to the most recent historical time period and the historical activity records, multiple possible activity types corresponding to the target mouse are determined; optionally, the time period type is morning, noon, evening, feeding time period or medication time period;

[0098] For each possible activity type, determine the energy consumption interval corresponding to the possible activity type according to the preset correspondence between the type and the consumption parameter interval;

[0099] Calculate the difference between the energy consumption parameter and the energy consumption interval to obtain the difference of the possible activity type;

[0100] Calculate the weighted sum average of the differences corresponding to all possible activity types to obtain the abnormal parameters corresponding to the target mouse;

[0101] Determine whether the abnormal parameter is greater than the preset parameter threshold and obtain the abnormal analysis result corresponding to the target mouse.

[0102] It can be seen that through the above-mentioned optional embodiments, it is possible to perform abnormal analysis on all possible activity types by means of energy consumption intervals corresponding to multiple possible activity types, and to realize abnormal analysis on mice after weighted calculation of the most accurate abnormal characterization parameters. It is possible to predict and analyze the energy consumption of mice more efficiently and accurately, improve the monitoring effect on mice, and provide a more accurate data basis for experimental research.

[0103] In a specific embodiment, a multi-channel mouse autonomous movement and energy metabolism detection system based on a single-chip microcomputer is realized, including (1) a detection cage: a running wheel, a temperature and humidity sensor, a stepper motor running wheel, a living area, and a rest area; (2) a drying system; (3) an air pump; (4) a carbon dioxide / oxygen analyzer; (5) a single-chip microcomputer (Beagleboard); (6) a backup power supply system; and (7) a computer. Specifically, each detection cage is equipped with a temperature and humidity sensor, a running wheel, and a Hall sensor, which are connected to a carbon dioxide and oxygen analysis system and a single-chip microcomputer. Through a self-compiled program, a variety of sensor information such as the mouse's movement distance, duration, and rhythm changes, carbon dioxide production, and oxygen consumption are collected in real time and dynamically. Then, the data processing method of the present invention is executed through a computer program preset in the computer to calculate the mouse's energy consumption parameters, and the single-chip microcomputer can change the running wheel resistance based on commands to verify other experimental conditions.

[0104] Embodiment 2

[0105] See also Figure 2 , Figure 2 Schematic diagram of a mouse metabolic monitoring data processing system based on multi-source information disclosed in an embodiment of the present invention. Figure 2 The described mouse metabolic monitoring data processing system based on multi-source information can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the mouse metabolism monitoring data processing system based on multi-source information may include:

[0106] The acquisition module 201 is used to acquire a plurality of initial sensing information of the target mouse by using a plurality of sensors arranged in the mouse activity area.

[0107] The encoding module 202 is used to encode each initial sensing information based on a data encoding algorithm to obtain corresponding encoded sensing information.

[0108] The prediction module 203 is used to predict the energy consumption parameters of the target mouse based on all the encoded sensor information based on the neural network algorithm.

[0109] The analysis module 204 is used to determine the abnormal analysis results corresponding to the energy consumption parameters according to the activity types of the target mice in the historical time period.

[0110] It can be seen that the above-mentioned embodiment of the invention can obtain multiple initial sensor information of the target mouse based on multiple sensors set in the mouse activity area, and predict the energy consumption parameters of the target mouse according to the neural network algorithm after data encoding to achieve subsequent accurate abnormality analysis, thereby being able to more efficiently and accurately predict and analyze the energy consumption of the mouse, improve the monitoring effect of the mouse, and provide a more accurate data basis for experimental research.

[0111] As an optional embodiment, the initial sensing information is temperature information, humidity information, carbon dioxide content, oxygen content, wheel speed, number of wheel revolutions, infrared sensing information or image information.

[0112] It can be seen that through the above-mentioned optional embodiments, the content of the sensor information is clarified, which can more comprehensively characterize the activities and behaviors of mice, so as to facilitate the subsequent accurate prediction of the energy consumption parameters of the target mice, assist in achieving more efficient and accurate prediction and analysis of the energy consumption of mice, improve the monitoring effect of mice, and provide a more accurate data basis for experimental research.

[0113] As an optional embodiment, the activity type is exercise activity, rest activity or eating activity.

[0114] It can be seen that through the above optional embodiments, the activity type is clarified, and the activity pattern of the mouse can be more comprehensively characterized, so as to facilitate the subsequent accurate analysis of the abnormal conditions of the energy consumption parameters of the mouse, and assist in achieving more efficient and accurate prediction and analysis of the energy consumption of the mouse, thereby improving the monitoring effect of the mouse and providing a more accurate data basis for experimental research.

[0115] As an optional embodiment, each initial sensing information is encoded based on a data encoding algorithm to obtain corresponding encoded sensing information, including:

[0116] For each piece of initial sensor information, the initial sensor information is cleaned according to a data cleaning rule to obtain the cleaned initial sensor information;

[0117] Determine a data encoding algorithm model corresponding to the initial sensing information according to the information type corresponding to the initial sensing information; optionally, the information type is temperature information, humidity information, carbon dioxide content, oxygen content, wheel speed, number of wheel revolutions, infrared sensing information or image information;

[0118] The cleaned initial sensor information is encoded according to a data encoding algorithm model to obtain corresponding encoded sensor information.

[0119] It can be seen that through the above-mentioned optional embodiments, the initial sensor information can be cleaned through the data cleaning rules and then the cleaned initial sensor can be encoded based on the data coding algorithm model corresponding to the information type to obtain the corresponding coded sensor information, so as to facilitate the subsequent accurate prediction of the energy consumption parameters of the target mice, assist in achieving more efficient and accurate prediction and analysis of the energy consumption of mice, improve the monitoring effect of mice, and provide a more accurate data basis for experimental research.

[0120] As an optional embodiment, the data encoding algorithm model includes a data normalization processing model and a data rearrangement algorithm model; the data normalization processing model is a CNN neural network, which is trained by a training data set including training sensor data corresponding to multiple information types and corresponding normalization parameter annotations; the data rearrangement algorithm model is an LSTM neural network model, which is trained by a training data set including training sensor data corresponding to multiple information types and corresponding data arrangement annotations.

[0121] It can be seen that through the above-mentioned optional embodiments, the details of the data coding algorithm model are clarified, and the normalization and rearrangement of the data can be realized to obtain coded sensor information with more predictive possibilities, so as to facilitate the subsequent accurate prediction of the energy consumption parameters of the target mice, and assist in achieving more efficient and accurate prediction and analysis of the energy consumption of mice, thereby improving the monitoring effect of mice and providing a more accurate data basis for experimental research.

[0122] As an optional embodiment, the encoding module encodes the cleaned initial sensor information according to the data encoding algorithm model to obtain the corresponding encoded sensor information, including:

[0123] Inputting the cleaned initial sensor information into a data normalization processing model to obtain output normalized sensor information;

[0124] The normalized sensor information is input into the data rearrangement algorithm model to obtain output coded sensor information.

[0125] It can be seen that through the above-mentioned optional embodiments, it is possible to achieve normalization and rearrangement of the data, and obtain coded sensor information with more predictive possibilities, so as to facilitate the subsequent accurate prediction of the energy consumption parameters of the target mice, assist in achieving more efficient and accurate prediction and analysis of the energy consumption of mice, improve the monitoring effect of mice, and provide a more accurate data basis for experimental research.

[0126] As an optional embodiment, the prediction module predicts the energy consumption parameters of the target mouse based on a neural network algorithm according to all encoded sensor information, including:

[0127] Input each coded sensor information into a trained energy consumption prediction neural network corresponding to the corresponding information type to obtain a predicted energy consumption parameter corresponding to each coded sensor information; optionally, the energy consumption prediction neural network is trained by a training data set including training coded sensor information corresponding to a plurality of information types and corresponding energy consumption parameter annotations;

[0128] The weighted sum average of the predicted energy expenditure parameters corresponding to all encoded sensor information was calculated to obtain the energy expenditure parameters of the target mouse.

[0129] It can be seen that through the above-mentioned optional embodiments, the neural network trained by multiple different types of training data can predict the predicted energy consumption parameters corresponding to different encoded sensor information, and the most accurate energy consumption parameters of the target mice can be obtained by weighted calculation, so as to facilitate the monitoring of mouse metabolism and subsequent abnormality analysis, and assist in achieving more efficient and accurate prediction and analysis of mouse energy consumption, improve the monitoring effect of mice, and provide a more accurate data basis for experimental research.

[0130] As an optional embodiment, the analysis module determines the specific manner of abnormal analysis results corresponding to the energy consumption parameters according to the activity type of the target mouse in the historical time period, including:

[0131] Obtain the historical activity records corresponding to the target mouse;

[0132] According to the time period type corresponding to the most recent historical time period and the historical activity records, multiple possible activity types corresponding to the target mouse are determined; optionally, the time period type is morning, noon, evening, feeding time period or medication time period;

[0133] For each possible activity type, determine the energy consumption interval corresponding to the possible activity type according to the preset correspondence between the type and the consumption parameter interval;

[0134] Calculate the difference between the energy consumption parameter and the energy consumption interval to obtain the difference of the possible activity type;

[0135] Calculate the weighted sum average of the differences corresponding to all possible activity types to obtain the abnormal parameters corresponding to the target mouse;

[0136] Determine whether the abnormal parameter is greater than the preset parameter threshold and obtain the abnormal analysis result corresponding to the target mouse.

[0137] It can be seen that through the above-mentioned optional embodiments, it is possible to perform abnormal analysis on all possible activity types by means of energy consumption intervals corresponding to multiple possible activity types, and to realize abnormal analysis on mice after weighted calculation of the most accurate abnormal characterization parameters. It is possible to predict and analyze the energy consumption of mice more efficiently and accurately, improve the monitoring effect on mice, and provide a more accurate data basis for experimental research.

[0138] Embodiment 3

[0139] See also Figure 3 , Figure 3 This is another mouse metabolism monitoring data processing system based on multi-source information disclosed in an embodiment of the present invention. Figure 3 The described mouse metabolic monitoring data processing system based on multi-source information is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the mouse metabolism monitoring data processing system based on multi-source information may include:

[0140] A memory 301 storing executable program codes;

[0141] a processor 302 coupled to the memory 301;

[0142] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the mouse metabolism monitoring data processing method based on multi-source information described in the first embodiment.

[0143] Embodiment 4

[0144] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the mouse metabolic monitoring data processing method based on multi-source information described in the first embodiment.

[0145] Embodiment 5

[0146] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the mouse metabolic monitoring data processing method based on multi-source information described in Example 1.

[0147] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0148] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0149] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0150] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0151] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0152] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0153] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0154] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0155] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0156] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0157] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0158] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0159] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0160] Finally, it should be noted that the mouse metabolic monitoring data processing method and system based on multi-source information disclosed in the embodiment of the present invention discloses only the preferred embodiment of the present invention, which is only used to illustrate the technical scheme of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical schemes described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical schemes from the spirit and scope of the technical schemes of the embodiments of the present invention.

Claims

1. A method for processing mouse metabolic monitoring data based on multi-source information, characterized in that: The method comprises: By setting up multiple sensors in the mouse activity area, multiple initial sensor information of the target mouse is obtained; Based on the data encoding algorithm, each of the initial sensing information is encoded to obtain corresponding encoded sensing information, including: For each of the initial sensor information, clean the initial sensor information according to a data cleaning rule to obtain the cleaned initial sensor information; According to the information type corresponding to the initial sensor information, determine the data encoding algorithm model corresponding to the initial sensor information; the information type is temperature information, humidity information, carbon dioxide content, oxygen content, wheel speed, number of wheel revolutions, infrared sensor information or image information; the data encoding algorithm model includes a data normalization processing model and a data rearrangement algorithm model; the data normalization processing model is a CNN neural network, which is obtained by training a training data set including a plurality of training sensor data corresponding to the information type and corresponding normalization parameter annotations; the data rearrangement algorithm model is an LSTM neural network model, which is obtained by training a training data set including a plurality of training sensor data corresponding to the information type and corresponding data arrangement annotations; Inputting the cleaned initial sensor information into the data normalization processing model to obtain output normalized sensor information; Inputting the normalized sensor information into the data rearrangement algorithm model to obtain output coded sensor information; Based on a neural network algorithm, predicting the energy expenditure parameters of the target mouse according to all the encoded sensor information; Determining the abnormal analysis result corresponding to the energy consumption parameter according to the activity type of the target mouse in the historical time period includes: Obtaining historical activity records corresponding to the target mouse; According to the time period type corresponding to the most recent historical time period and the historical activity records, multiple possible activity types corresponding to the target mouse are determined; the time period types are morning, noon, evening, feeding time period or medication time period; For each of the possible activity types, determining the energy consumption interval corresponding to the possible activity type according to the correspondence between the preset type and the consumption parameter interval; Calculating the difference between the energy consumption parameter and the energy consumption interval to obtain the difference of the possible activity type; Calculating the weighted sum average of the differences corresponding to all the possible activity types to obtain the abnormal parameters corresponding to the target mouse; It is determined whether the abnormal parameter is greater than a preset parameter threshold value to obtain the abnormal analysis result corresponding to the target mouse.

2. The method for processing mouse metabolic monitoring data based on multi-source information according to claim 1, characterized in that: The activity type is exercise activity, rest activity or eating activity.

3. The method for processing mouse metabolic monitoring data based on multi-source information according to claim 1, characterized in that: The method of predicting the energy consumption parameters of the target mouse based on all the coded sensor information based on the neural network algorithm includes: Input each of the coded sensor information into a trained energy consumption prediction neural network corresponding to the corresponding information type to obtain a predicted energy consumption parameter corresponding to each of the coded sensor information; the energy consumption prediction neural network is trained by a training data set including training coded sensor information corresponding to a plurality of information types and corresponding energy consumption parameter annotations; The weighted sum average of the predicted energy consumption parameters corresponding to all the encoded sensor information is calculated to obtain the energy consumption parameter of the target mouse.

4. A mouse metabolic monitoring data processing system based on multi-source information, characterized in that: The system comprises: An acquisition module, used for acquiring a plurality of initial sensing information of a target mouse through a plurality of sensors arranged in an activity area of ​​the mouse; The encoding module is used to encode each of the initial sensing information based on a data encoding algorithm to obtain corresponding encoded sensing information, including: For each of the initial sensor information, clean the initial sensor information according to a data cleaning rule to obtain the cleaned initial sensor information; According to the information type corresponding to the initial sensor information, determine the data encoding algorithm model corresponding to the initial sensor information; the information type is temperature information, humidity information, carbon dioxide content, oxygen content, wheel speed, number of wheel revolutions, infrared sensor information or image information; the data encoding algorithm model includes a data normalization processing model and a data rearrangement algorithm model; the data normalization processing model is a CNN neural network, which is obtained by training a training data set including a plurality of training sensor data corresponding to the information type and corresponding normalization parameter annotations; the data rearrangement algorithm model is an LSTM neural network model, which is obtained by training a training data set including a plurality of training sensor data corresponding to the information type and corresponding data arrangement annotations; Inputting the cleaned initial sensor information into the data normalization processing model to obtain output normalized sensor information; Inputting the normalized sensor information into the data rearrangement algorithm model to obtain output coded sensor information; A prediction module, used for predicting the energy consumption parameters of the target mouse based on all the encoded sensor information based on a neural network algorithm; The analysis module is used to determine the abnormal analysis result corresponding to the energy consumption parameter according to the activity type of the target mouse in the historical time period, including: Obtaining historical activity records corresponding to the target mouse; According to the time period type corresponding to the most recent historical time period and the historical activity records, multiple possible activity types corresponding to the target mouse are determined; the time period types are morning, noon, evening, feeding time period or medication time period; For each of the possible activity types, determining the energy consumption interval corresponding to the possible activity type according to the correspondence between the preset type and the consumption parameter interval; Calculating the difference between the energy consumption parameter and the energy consumption interval to obtain the difference of the possible activity type; Calculating the weighted sum average of the differences corresponding to all the possible activity types to obtain the abnormal parameters corresponding to the target mouse; It is determined whether the abnormal parameter is greater than a preset parameter threshold value to obtain the abnormal analysis result corresponding to the target mouse.

5. A mouse metabolic monitoring data processing system based on multi-source information, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the mouse metabolic monitoring data processing method based on multi-source information as described in any one of claims 1-3.

Images