Data acquisition method, device, equipment, readable storage medium and program product

Abstract

The application relates to a data acquisition method, device, equipment, readable storage medium and program product. The method comprises the following steps: acquiring a plurality of initial sample data; for one initial sample data, temperature interval extraction is performed on a first temperature interval and a second temperature interval according to a preset sample expansion multiple, a plurality of first temperature subintervals corresponding to the first temperature interval and a plurality of second temperature subintervals corresponding to the second temperature interval are obtained, sample expansion processing is performed on an input data sequence according to the plurality of first temperature subintervals, sample expansion processing is performed on a label data sequence according to the plurality of second temperature subintervals, and a plurality of target sample data are obtained. The initial sample data comprises the input data sequence and a label data sequence corresponding to the input data sequence, the input data sequence corresponds to the first temperature interval, and the label data sequence corresponds to the second temperature interval. The method can reduce the sample data acquisition cost.

Description

Technical Field

[0001] This application relates to the field of thermal engineering technology, and in particular to a data acquisition method, apparatus, device, readable storage medium, and program product. Background Technology

[0002] With the development of artificial intelligence technology, artificial intelligence models are widely used in various industries, such as the field of thermal engineering. Thermal characteristics can be described by thermal characteristic models. However, during the development process, a large amount of sample data is required for training in order to obtain a mature and usable model.

[0003] Traditional methods of obtaining sample data typically involve researchers conducting experiments under different pre-set conditions to obtain the sample data needed for model training.

[0004] However, the above-mentioned methods for obtaining sample data have the problem of high acquisition costs. Summary of the Invention

[0005] Therefore, it is necessary to provide a data acquisition method, apparatus, device, readable storage medium, and program product that can reduce the cost of acquiring sample data in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a data acquisition method, including:

[0007] Multiple initial sample data are acquired. The initial sample data includes an input data sequence and a label data sequence corresponding to the input data sequence. The input data sequence corresponds to a first temperature range, and the label data sequence corresponds to a second temperature range.

[0008] For an initial sample data, temperature ranges are extracted from the first temperature range and the second temperature range according to a preset sample expansion factor, resulting in multiple first temperature sub-ranges corresponding to the first temperature range and multiple second temperature sub-ranges corresponding to the second temperature range.

[0009] The input data sequence is augmented based on multiple first temperature sub-intervals, and the label data sequence is augmented based on multiple second temperature sub-intervals to obtain multiple target sample data.

[0010] In one embodiment, temperature range extraction is performed on the first temperature range and the second temperature range according to a preset sample augmentation factor, resulting in multiple first temperature sub-ranges corresponding to the first temperature range and multiple second temperature sub-ranges corresponding to the second temperature range, including:

[0011] Based on the sample augmentation factor and the first interval conversion condition, multiple first temperature points are determined;

[0012] Based on the sample augmentation factor and the second interval conversion conditions, multiple second temperature points were determined;

[0013] Based on each first temperature point, the first temperature interval is extracted to obtain multiple first temperature sub-intervals, and based on each second temperature point, the second temperature interval is extracted to obtain multiple second temperature sub-intervals.

[0014] In one embodiment, a first temperature range is extracted based on each first temperature point to obtain multiple first temperature sub-ranges, and a second temperature range is extracted based on each second temperature point to obtain multiple second temperature sub-ranges, including:

[0015] Obtain the first starting point corresponding to the first temperature range and the second starting point corresponding to the second temperature range;

[0016] For a given first temperature point, the temperature range between the first starting point and the first temperature point is defined as a first temperature sub-range.

[0017] For a given second temperature point, the temperature range between the second starting point and the second temperature point is defined as a second temperature sub-range.

[0018] In one embodiment, the input data sequence is augmented according to multiple first temperature sub-intervals, and the tag data sequence is augmented according to multiple second temperature sub-intervals to obtain multiple target sample data, including:

[0019] For a first temperature sub-interval, multiple first sampling temperature points are determined based on the number of first sampling points and the first sampling conversion conditions, and each first sampling temperature point is located within the first temperature sub-interval.

[0020] For the second temperature sub-interval corresponding to the first temperature sub-interval, multiple second sampling temperature points are determined based on the number of second sampling points and the second sampling conversion conditions, and each second sampling temperature point is located within the second temperature sub-interval.

[0021] The target sample data in the first temperature sub-interval and the corresponding second temperature sub-interval are determined based on the input data sequence fragments corresponding to each first sampling temperature point, each second sampling temperature point, the first temperature sub-interval, and the label data sequence fragments corresponding to the second temperature sub-interval.

[0022] In one embodiment, the target sample data within the first temperature sub-interval is determined based on each first sampling temperature point, each second sampling temperature point, the input data sequence fragment corresponding to the first temperature sub-interval, and the tag data sequence fragment corresponding to the second temperature sub-interval, including:

[0023] Based on the input data sequence segment corresponding to the first temperature sub-interval and the first interpolation condition, determine the sampling input data corresponding to each first sampling temperature point;

[0024] Based on the tag data sequence fragments corresponding to the second temperature sub-interval and the second preset interpolation conditions, determine the sampling tag data corresponding to each second sampling temperature point;

[0025] The target sample data corresponding to the first temperature sub-interval is determined based on each sampled input data and each sampled label data.

[0026] In one embodiment, determining the target sample data corresponding to the first temperature sub-interval based on each sampled input data and each sampled label data includes:

[0027] The target sampling label data in each sampling label data is taken as the target label data, and the order of the second sampling temperature points corresponding to the target sampling label data in the second temperature sub-interval satisfies the preset condition.

[0028] Each sampled input data is used as the target input data;

[0029] The target input data and target label data are used as target sample data.

[0030] Secondly, this application also provides a model training method, including:

[0031] Multiple target sample data are acquired using the data acquisition method provided in any embodiment of the first aspect;

[0032] The initial model is iteratively trained using multiple target sample data to obtain the target model, which is used to determine the label data corresponding to the input data based on the input data.

[0033] Thirdly, this application also provides a data acquisition device, comprising:

[0034] The acquisition module is used to acquire multiple initial sample data, which include an input data sequence and a label data sequence corresponding to the input data sequence. The input data sequence corresponds to a first temperature range, and the label data sequence corresponds to a second temperature range.

[0035] The temperature range extraction module is used to extract temperature ranges from the first temperature range and the second temperature range according to a preset sample expansion factor for an initial sample data, so as to obtain multiple first temperature sub-ranges corresponding to the first temperature range and multiple second temperature sub-ranges corresponding to the second temperature range.

[0036] The target module is used to perform sample augmentation processing on the input data sequence based on multiple first temperature sub-intervals, and to perform sample augmentation processing on the label data sequence based on multiple second temperature sub-intervals, so as to obtain multiple target sample data.

[0037] Fourthly, embodiments of this application provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in the first aspect above.

[0038] Fifthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described in the first aspect above.

[0039] Sixthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in the first aspect above.

[0040] The aforementioned data acquisition method, apparatus, device, readable storage medium, and program product, by acquiring multiple initial sample data, can extract temperature ranges for a first temperature range and a second temperature range respectively according to a preset sample amplification factor for a single initial sample data, thereby obtaining multiple first temperature sub-ranges corresponding to the first temperature range and multiple second temperature sub-ranges corresponding to the second temperature range. Then, the input data sequence is sample amplified based on the multiple first temperature sub-ranges, and the tag data sequence is sample amplified based on the multiple second temperature sub-ranges to obtain multiple target sample data. The initial sample data includes the input data sequence and the tag data sequence corresponding to the input data sequence. The input data sequence corresponds to the first temperature range, and the tag data sequence corresponds to the second temperature range. In this way, based on the desired sample expansion factor, the temperature range corresponding to the first temperature range of the input data sequence used to input the model in the initial sample data is extracted, and the temperature range corresponding to the label data sequence of the input data sequence is extracted, resulting in multiple sets of first temperature sub-ranges and second temperature sub-ranges. Based on each first temperature sub-range and second temperature sub-range, multiple expanded target sample data are obtained. The number of target sample data obtained is the product of the original initial sample data and the sample expansion factor, which greatly increases the scale of the sample data and reduces the cost of obtaining sample data. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is an application environment diagram of a data acquisition method in one embodiment;

[0043] Figure 2 This is a flowchart illustrating a data acquisition method in one embodiment;

[0044] Figure 3 This is a schematic diagram of the initial sample data obtained from a set of experiments in another embodiment;

[0045] Figure 4 This is a flowchart illustrating step 202 in another embodiment;

[0046] Figure 5 This is a flowchart illustrating step 203 in another embodiment;

[0047] Figure 6 This is a flowchart illustrating an exemplary data acquisition method in another embodiment;

[0048] Figure 7 This is a flowchart illustrating a model training method in one embodiment;

[0049] Figure 8 This is a schematic diagram illustrating the input and output dimensions of the model in another embodiment;

[0050] Figure 9 This is a flowchart illustrating the model training process in another embodiment;

[0051] Figure 10 This is a schematic diagram illustrating how the loss value changes with the number of iterations in another embodiment;

[0052] Figure 11 This is a schematic diagram comparing the average interpolation value with the test loss value in another embodiment;

[0053] Figure 12 This is a schematic diagram comparing predicted label data and target label data in another embodiment;

[0054] Figure 13 This is a schematic diagram of the second predicted label data and the second loss value in another embodiment;

[0055] Figure 14 This is a structural block diagram of a data acquisition device in one embodiment;

[0056] Figure 15 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0058] With the development of artificial intelligence technology, AI models are widely used in various industries, such as the field of thermal engineering. In the field of thermal engineering, there are still many conversion reaction mechanisms and problems that are not fully understood. Using AI methods, researchers can build "black box" models based on sufficient experimental data to accurately describe or predict the characteristics of samples. However, in the process of model development, a large amount of sample data is required for training in order to obtain a mature and usable model. The scale of the sample data usually needs to reach millions or more.

[0059] Compared to applications such as image recognition and language processing, obtaining data samples in the field of engineering research is much more difficult. In the traditional field of thermal engineering, the method of obtaining sample data usually involves researchers conducting experiments under different preset conditions to obtain the sample data required for model training.

[0060] However, experiments are very expensive; obtaining a large amount of sample data through experiments requires extremely high costs.

[0061] In addition, sample data from different sources (such as different researchers or different experimental environments leading to different sources of sample data) are unreliable when training models.

[0062] In view of this, this application provides a data acquisition method, apparatus, device, readable storage medium, and program product. By acquiring multiple initial sample data, temperature range extraction can be performed on a first temperature range and a second temperature range according to a preset sample expansion factor for a single initial sample data, resulting in multiple first temperature sub-ranges corresponding to the first temperature range and multiple second temperature sub-ranges corresponding to the second temperature range. Then, the input data sequence is sample-expanded based on the multiple first temperature sub-ranges, and the tag data sequence is sample-expanded based on the multiple second temperature sub-ranges to obtain multiple target sample data. The initial sample data includes an input data sequence and a tag data sequence corresponding to the input data sequence. The input data sequence corresponds to the first temperature range, and the tag data sequence corresponds to the second temperature range. In this way, based on the desired sample expansion factor, the temperature range corresponding to the first temperature range of the input data sequence used to input the model in the initial sample data is extracted, and the temperature range corresponding to the label data sequence of the input data sequence is extracted, resulting in multiple sets of first temperature sub-ranges and second temperature sub-ranges. Based on each first temperature sub-range and second temperature sub-range, multiple expanded target sample data are obtained. The number of target sample data obtained is the product of the original initial sample data and the sample expansion factor, which greatly increases the scale of the sample data and reduces the cost of obtaining sample data.

[0063] The data acquisition method provided in this application embodiment can be applied to, for example... Figure 1 The application environment shown is illustrated. The data storage system stores the data that server 101 needs to process. The data storage system can be integrated onto server 101, or it can be located on the cloud or other network servers. Server 101 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0064] In one exemplary embodiment, such as Figure 2 As shown, a data acquisition method is provided, which can be applied to... Figure 1 Taking server 101 as an example, it can be understood that this method can also be applied to terminals, and also to systems including terminals and servers, and is implemented through the interaction between the terminal and the server. The method includes the following steps 201 to 203. Wherein:

[0065] Step 201: Obtain multiple initial sample data.

[0066] Initial sample data can be sample data obtained after conducting at least one experiment on a thermal sample (such as a battery). The initial sample data includes the input data sequence and the corresponding tag data sequence.

[0067] Let the input data sequence be X (k) , representing the k-th input data sequence, and the corresponding label data sequence is Y. (k) Let represent the k-th label data sequence, then the k-th initial sample data can be denoted as (X). (k) Y (k) ), k={1,2,……,K}.

[0068] The input data sequence can be temperature-related data used to input artificial intelligence models. In the embodiments of this application, the input data sequence can characterize certain thermal properties of thermal samples at different temperatures, such as the heat generation power characteristics of battery positive and negative electrodes and electrolyte materials.

[0069] Optionally, the input data sequence may include only one type of thermal characteristic data, or alternatively, the input data sequence may include multiple types of thermal characteristic data.

[0070] The tag input sequence can be temperature-related data that is affected by the input data sequence. It is also the data that the artificial intelligence model wants to obtain after analyzing the input data sequence. The tag input sequence can also characterize certain thermal properties of thermal samples at different temperatures, such as the temperature rise rate characteristics of thermal samples at different temperatures. This temperature rise rate is affected by the heat generation power characteristics of the positive and negative electrodes and electrolyte materials of the battery.

[0071] Optionally, the input data sequence may include only one type of thermal characteristic data, or alternatively, the input data sequence may include multiple types of thermal characteristic data.

[0072] The input data sequence corresponds to the first temperature range, and the tag data sequence corresponds to the second temperature range. In this embodiment, the first temperature range may be the same as or different from the second temperature range.

[0073] It is understandable that both the first and second temperature ranges are monotonically increasing or monotonically decreasing. For example, the first temperature range could be 0-300℃, while the second temperature range could be 600-300℃.

[0074] Taking a battery as an example, a battery is composed of a positive electrode, a negative electrode, an electrolyte, a current collector, a separator, tabs, and a battery casing, etc., through a certain structure. During the process from self-heating to complete thermal runaway and scrapping of the battery, complex thermochemical reactions occur between the positive electrode, negative electrode, electrolyte, and other materials inside the battery, leading to a continuous increase in battery temperature. In the embodiments of this application, the model can be used to determine the relationship between the heat generation power characteristics of the positive and negative electrode and electrolyte materials and the temperature rise rate. That is, the corresponding temperature rise rate is determined according to the heat generation power characteristics of the positive and negative electrode and electrolyte materials. The input data sequence can include the heat generation power of the positive electrode material, the heat generation power of the negative electrode material, the heat generation power of the positive electrode + negative electrode material, the heat generation power of the positive electrode + electrolyte, the heat generation power of the negative electrode + electrolyte, etc., while the tag data sequence can include the temperature rise rate characteristics.

[0075] Regarding the process of obtaining initial sample data, in one possible implementation, the server can determine the specific data included in the input data sequence and label data sequence based on the target of the model input and output. Then, it can conduct experiments under preset conditions based on the specific data included in the input data sequence and label data sequence to obtain multiple initial sample data.

[0076] In this embodiment, if the input data sequence includes the heat generation power of the positive electrode material, the heat generation power of the negative electrode material, the heat generation power of the positive electrode + negative electrode material, the heat generation power of the positive electrode + electrolyte, and the heat generation power of the negative electrode + electrolyte, a calorimeter (such as a differential scanning calorimeter) can be used in the experiment to test batteries of different materials or different material combinations under linear heating conditions to obtain the heat generation power curves corresponding to batteries of different materials or different material combinations, thereby obtaining data such as the heat generation power of the positive electrode material, the heat generation power of the negative electrode material, the heat generation power of the positive electrode + negative electrode material, the heat generation power of the positive electrode + electrolyte, and the heat generation power of the negative electrode + electrolyte; if the output data sequence includes temperature rise rate data, an adiabatic accelerated calorimeter can be used in the experiment to test batteries of different materials or different material combinations to obtain the temperature rise rate curve corresponding to the input data sequence, as shown in the reference. Figure 3 , which is the initial sample data obtained from a set of experiments, including.

[0077] Optionally, the server can obtain the initial sample data input by the user through an external input device; alternatively, the server can directly obtain the stored initial sample data from the database.

[0078] Step 202: For an initial sample data, extract the temperature ranges of the first temperature range and the second temperature range according to the preset sample expansion factor to obtain multiple first temperature sub-ranges corresponding to the first temperature range and multiple second temperature sub-ranges corresponding to the second temperature range.

[0079] The cost of a single experiment is too high. For example, the differential scanning calorimeter for testing input data sequences such as the heat generation power of positive electrode material, the heat generation power of negative electrode material, the heat generation power of positive electrode + negative electrode material, the heat generation power of positive electrode + electrolyte, and the heat generation power of negative electrode + electrolyte takes 3 hours and costs 1,000 yuan per experiment. The adiabatic accelerated calorimeter required for detecting tag data sequences including temperature rise rate takes 48 hours and costs 50,000 yuan per experiment. If you want to obtain a large-scale sample data, the cost is too high. In order to save costs, in this embodiment of the application, after obtaining multiple sets of initial sample data, the server can obtain a preset sample expansion factor and expand the initial sample data according to the preset sample expansion factor to obtain the target sample data of the preset data scale.

[0080] The preset sample expansion factor is the desired expansion factor of the initial sample data. In this embodiment, the sample expansion factor can be determined based on the model parameters and the amount of initial sample data. Referring to formula (1), the sample expansion factor is λ, K is the amount of initial sample data, and ε is the number of model parameters.

[0081]

[0082] The amount of target sample data obtained after expansion is N, where N = λK.

[0083] After obtaining the sample augmentation factor and the initial sample data, the server can augment the initial sample data. In this embodiment, a temperature range extraction concept is introduced. The server can extract the temperature ranges corresponding to the first temperature range of the input data sequence and the second temperature range corresponding to the label data sequence according to the sample augmentation factor, thereby obtaining multiple input data sequence fragments corresponding to the first temperature sub-ranges and multiple label data sequence fragments corresponding to the second temperature sub-ranges. This cuts the initial sample data into multiple sample data, increasing the number of sample data.

[0084] In one possible implementation, a temperature range extraction concept based on reaction kinetics is introduced. In engineering applications such as thermal engineering, the thermal properties characterized by sample data are typically determined by kinetic processes within a temperature range, such as thermal characteristic-temperature curves. The thermal properties of a sample (such as a battery) at a certain moment are related to its historical temperature changes. Therefore, in this embodiment, the server can obtain multiple first temperature points for temperature range extraction corresponding to a first temperature range and multiple second temperature points for temperature range extraction corresponding to a second temperature range, based on the sample augmentation factor. Then, the starting point of the first temperature range is used as the starting point of each first temperature sub-range, the starting point of the second temperature range is used as the starting point of each second temperature sub-range, and each temperature point is used as the ending point of each temperature sub-range, thereby obtaining multiple first temperature sub-ranges and multiple second temperature sub-ranges. For example, if the first temperature range is 0-300℃ and the first temperature points include 100℃ and 150℃, then the first temperature sub-ranges include 0-100℃, 0-150℃, and 0-300℃.

[0085] Step 203: Perform sample augmentation processing on the input data sequence according to multiple first temperature sub-intervals, and perform sample augmentation processing on the label data sequence according to multiple second temperature sub-intervals to obtain multiple target sample data.

[0086] After obtaining multiple first temperature sub-intervals and second temperature sub-intervals based on the first temperature interval and the second temperature interval, the input data sequence and the label data sequence are naturally divided into multiple input data sequence segments corresponding to each first temperature sub-interval and multiple label data sequence segments corresponding to each second temperature sub-interval. At this time, the server can perform expansion processing on each input data sequence segment and each label data sequence segment to obtain multiple target sample data.

[0087] Optionally, the server can input each input data sequence fragment and each label data sequence fragment into the trained augmented model to obtain augmented input data and label data. The server can then use these augmented input data and label data as target sample data.

[0088] Optionally, the input data sequence segment includes multiple input data, and the label data sequence segment includes multiple label data. The server can perform interpolation processing on the input data sequence segment based on the input data in the input data sequence segment to obtain an expanded input data sequence segment. The server can use the expanded input data sequence segment as the target input data. The same expansion method can be used for the label data sequence segment to obtain an expanded label data sequence segment. The server can use the expanded label data sequence segment as the target label data. Finally, the target input data and the target label data are used as the target sample data.

[0089] In one possible implementation, after obtaining a large amount of target sample data, the server can use the target sample data for model training.

[0090] In the above embodiments, the server extracts the temperature range corresponding to the first temperature range of the input data sequence used to input the model in the initial sample data according to the desired sample expansion factor, and extracts the temperature range of the second temperature range to which the label data sequence corresponding to the input data sequence belongs, thus obtaining multiple sets of first temperature sub-ranges and second temperature sub-ranges. Based on each first temperature sub-range and second temperature sub-range, multiple expanded target sample data are obtained. The number of target sample data obtained is the product of the original initial sample data and the sample expansion factor, which greatly increases the scale of sample data and reduces the cost of obtaining sample data.

[0091] In one embodiment, based on the above Figure 2 The illustrated embodiment can be found in [reference]. Figure 4 This embodiment involves extracting temperature ranges from a first temperature range and a second temperature range according to a preset sample augmentation factor, thereby obtaining multiple first temperature sub-ranges corresponding to the first temperature range and multiple second temperature sub-ranges corresponding to the second temperature range. For example... Figure 4 As shown, step 202 may include steps 401 to 403.

[0092] Step 401: Determine multiple first temperature points based on the sample expansion factor and the first interval conversion conditions.

[0093] Step 402: Determine multiple second temperature points based on the sample expansion factor and the second interval conversion conditions.

[0094] Step 403: Extract the temperature range of the first temperature range according to each first temperature point to obtain multiple first temperature sub-ranges, and extract the temperature range of the second temperature range according to each second temperature point to obtain multiple second temperature sub-ranges.

[0095] For the first temperature range, the server can first obtain multiple first temperature points for segmentation. Regarding the method of obtaining the first temperature points, in this embodiment of the application, the server can determine the number of temperature sub-ranges extracted from the first temperature range according to the sample expansion factor, thereby determining the number of first temperature points. For example, if the first temperature range is 0-300℃ and the sample expansion factor is 3, it means that the first temperature range needs to be generated into 3 first temperature sub-ranges, so the number of first temperature points is 3, and the last point is the end point of the first temperature range, i.e., 300℃.

[0096] After determining the number of first temperature points, the server can first generate a sequence of rational numbers corresponding to each first temperature point, denoted as Z. λ (i)=i,{i=1,2,...,λ}.

[0097] Then, the server can transform the rational number sequence corresponding to each first temperature point according to the first interval transformation condition to obtain multiple first temperature points. The transformation process can be referred to the following formula:

[0098] T X (i)=f TX (Z λ (i)), i=1,2,…,λ (2)

[0099] Among them, T X (i) represents the i-th first temperature point, X represents the input data, and f TX () represents the transformation formula corresponding to the first interval transformation condition. This transformation formula can be determined based on the first interval transformation condition, which can be a linear transformation, polynomial transformation, exponential transformation, logarithmic transformation, etc.

[0100] Similarly, for the second temperature range, the server can obtain multiple second temperature points based on the sample augmentation factor and the second range conversion conditions. The conversion process can be referred to the following formula:

[0101] T Y (i)=f TY (Z λ (i)), i=1,2,…,λ (3)

[0102] Among them, T Y (i) represents the i-th second temperature point, Y represents the tag data, and f TY () represents the transformation formula corresponding to the second interval transformation condition. This transformation formula can be determined based on the second interval transformation condition. The first interval transformation condition can be a linear transformation, a polynomial transformation, an exponential transformation, a logarithmic transformation, etc.

[0103] It is understandable that f TX () and fTY () in the transition interval Z λ All of them are monotonic functions.

[0104] After obtaining the first temperature point corresponding to the first temperature range and the second temperature point corresponding to the second temperature range, the server performs temperature range extraction processing on each temperature range. Regarding the temperature range extraction processing, in one possible implementation, the server can obtain the first starting point corresponding to the first temperature range and the second starting point corresponding to the second temperature range. Then, for a first temperature point, the temperature range between the first starting point and the first temperature point is determined as a first temperature sub-range. For a second temperature point, the temperature range between the second starting point and the second temperature point is determined as a second temperature sub-range.

[0105] In the above embodiments, the first starting point is the temperature at the beginning of the first temperature range, and the second starting point is the temperature at the beginning of the second temperature range. For example, if the first temperature range is 0-300℃, then the first starting point is 0℃, and if the second temperature range is 600-200℃, then the second starting point is 600℃.

[0106] For a first temperature point, the temperature range between the first starting point and the first temperature point is defined as a first temperature sub-range. For a second temperature point, the temperature range between the second starting point and the second temperature point is defined as a second temperature sub-range. For example, if the first starting point is 0℃, the second starting point is 600℃, the first temperature points are 10℃, 100℃, and 200℃, and the second temperature points are 550℃, 450℃, and 350℃, then the first temperature sub-ranges are 0-10℃, 0-100℃, and 0-200℃, and the second temperature sub-ranges are 600-550℃, 600-450℃, and 600-350℃.

[0107] The process of obtaining each first temperature sub-interval and each second temperature sub-interval can be referred to the following formula:

[0108]

[0109] Among them, T X1 T represents the first starting point. Y1 Represents the second starting point, range(T) X,i ) represents the first temperature sub-interval corresponding to the i-th first temperature point, range(T) Y,i ) represents the second temperature sub-interval corresponding to the i-th second temperature point.

[0110] In one embodiment, based on the above Figure 2 The illustrated embodiment can be found in [reference]. Figure 5This embodiment involves a process of augmenting an input data sequence based on multiple first temperature sub-intervals and augmenting a label data sequence based on multiple second temperature sub-intervals to obtain multiple target sample data. For example... Figure 5 As shown, step 203 may include steps 501 to 503.

[0111] Step 501: For a first temperature sub-interval, determine multiple first sampling temperature points based on the number of first sampling points and the first sampling conversion conditions.

[0112] Each of the first sampling temperature points is located within the first temperature sub-interval.

[0113] Step 502: For the second temperature sub-interval corresponding to the first temperature sub-interval, determine multiple second sampling temperature points based on the number of second sampling points and the second sampling conversion conditions.

[0114] Each of the second sampling temperature points is located within the second temperature sub-interval.

[0115] Step 503: Determine the target sample data in the first temperature sub-interval and the corresponding second temperature sub-interval based on the input data sequence fragments corresponding to each first sampling temperature point, each second sampling temperature point, the first temperature sub-interval, and the label data sequence fragments corresponding to the second temperature sub-interval.

[0116] The first number of sampling points is the number of sampling points that are desired to be included in the first temperature sub-interval. Similarly, the second number of sampling points is the number of sampling points that are desired to be included in the second temperature sub-interval. In this embodiment, the number of sampling points can be selected by researchers according to the actual application scenario, and the value is generally between 10 and 10,000. The first number of sampling points and the second number of sampling points can be different.

[0117] For a given first temperature sub-interval, the server can generate a sequence of first sampling points corresponding to the first temperature sub-interval, denoted as Zγ, based on the number of first sampling points and the number of second sampling points. x (j x )=j,j x ={1,2,…,γx}, where γ x Given the number of the first sampling points, similarly, the server can generate the second sampling point sequence corresponding to the second temperature sub-interval, denoted as Zγ. Y (j Y )=j,j Y ={1,2,……,γ Y}, where γ Y This represents the number of the second sampling points.

[0118] For a given first temperature sub-interval, the server can determine multiple first sampling temperature points based on the sampling point sequence and the first sampling transformation conditions. The transformation process can be referenced using the following formula:

[0119] T X,i (j X )=f TX,i (Z γX (j X )),j X =1,2,…,γ X (5)

[0120] Among them, T x,i (j x ) represents the j-th temperature in the i-th first temperature sub-interval. x The first sampling temperature point, f TX,i () represents the first sampling transformation condition corresponding to the first temperature sub-interval. This first sampling transformation condition can be a simple prior transformation relation or a polynomial transformation, exponential transformation, logarithmic transformation, etc.

[0121] Similarly, for a second temperature sub-interval, the server can determine multiple second sampling temperature points based on the sampling point sequence and the corresponding second sampling transformation conditions. The transformation process can be referred to the following formula:

[0122] T Y,i (j Y )=f TY,i (Z γY (j Y )),j Y =1,2,…,γ Y (6)

[0123] Among them, T Y,j (j Y ) represents the j-th temperature in the i-th second temperature sub-interval. Y The second sampling temperature point, f TY,i () represents the second sampling transformation condition corresponding to the second temperature sub-interval. This second sampling transformation condition can be a simple prior transformation relation or a polynomial transformation, exponential transformation, logarithmic transformation, etc.

[0124] After obtaining multiple first sampling temperature points and multiple second sampling temperature points, the server can determine the target sample data within the first temperature sub-interval based on each first sampling temperature point, each second sampling temperature point, the input data sequence fragment corresponding to the first temperature sub-interval, and the label data sequence fragment corresponding to the second temperature sub-interval.

[0125] In one possible implementation, the process may include the following steps: the server determines the sampling input data corresponding to each first sampling temperature point based on the input data sequence segment corresponding to the first temperature sub-interval and the first interpolation condition; the server determines the sampling label data corresponding to each second sampling temperature point based on the label data sequence segment corresponding to the second temperature sub-interval and the second preset interpolation condition; the server determines the target sample data within the first temperature sub-interval and the second temperature sub-interval corresponding to the first temperature sub-interval based on each sampling input data and each sampling label data.

[0126] It is understandable that the input data sequence fragments corresponding to the first temperature sub-interval and the label data sequence fragments corresponding to the second temperature sub-interval are both discrete data. Therefore, the input data corresponding to each first sampling temperature point and the label data corresponding to each second sampling temperature point may not exist. In order to obtain the data corresponding to each sampling temperature point, the server can perform interpolation processing based on each sampling temperature point.

[0127] For multiple first sampling temperature points included in the first temperature sub-interval, the server can perform interpolation processing based on the input data sequence segment corresponding to the first temperature sub-interval and the first interpolation condition, thereby obtaining the sampling input data corresponding to each first sampling temperature point. Regarding the first interpolation condition, the server can select it according to the actual application conditions, such as linear interpolation, polynomial interpolation, spline curve interpolation, etc. The interpolation process can be referenced using the following formula:

[0128] X i =interpX(T X ,X,T X,i ), i=1,2,…,λ (7)

[0129] T X X represents the first temperature sub-interval, and T represents the input data. X,i This indicates that the first temperature sub-interval is the i-th, X i This represents the thermal characteristic curve corresponding to the first temperature sub-range. The server can determine this based on X. i Determine the set of sampling input data corresponding to each first sampling temperature point.

[0130] Similarly, the server can perform interpolation based on the tag data sequence fragments corresponding to the second temperature sub-interval and the second interpolation conditions to obtain the sampling input data corresponding to each second sampling temperature point. Regarding the second interpolation conditions, the server can select them according to the actual application conditions, such as linear interpolation, polynomial interpolation, spline curve interpolation, etc. The interpolation process can be referenced using the following formula:

[0131] Y i =interpY(T Y,Y,T Y,i ), i=1,2,…,λ (8)

[0132] T Y Y represents the second temperature sub-interval, and T represents the label data. Y,i This indicates that the second temperature sub-interval is the i-th, Y i This represents the thermal characteristic curve corresponding to the second temperature sub-range. The server can determine this based on Y. i Determine the set of sampling label data corresponding to each first sampling temperature point.

[0133] In one possible implementation, after obtaining the sampling input data and the sampling label data, the server can directly use the sampling input data corresponding to each first temperature sub-interval as the target input data, and the sampling label data corresponding to each second temperature sub-interval corresponding to each first temperature sub-interval as the target label data. Finally, the target input data and the target label data are used as the target sample data, which can be denoted as... It can be seen that dividing each initial sample data into λ parts greatly increases the amount of sample data.

[0134] In another possible implementation, since the tag data can be the tags of each sampled input data in the first temperature sub-interval, the server can assume that the tag data corresponding to each sampled input data is consistent for a first temperature sub-interval. Then the server can set the number of second sampling points to 1. Accordingly, there is only 1 sampled tag data corresponding to the second temperature sub-interval. The server can use this sampled tag data as the target tag data, which can reduce the waste of computing resources.

[0135] In this embodiment of the application, the process by which the server determines the target sample data corresponding to the first temperature sub-interval based on each sampled input data and each sampled label data may include the following steps: the server uses the target sampled label data in each sampled label data as the target label data; the server uses each sampled input data as the target input data; and the server uses the target input data and the target label data as the target sample data.

[0136] Understandably, for a first temperature sub-interval, the server can assume that the label data corresponding to each sampled input data is consistent. Therefore, the server can select a target sampled label data from multiple sampled label data as the target label data. The order of the second sampled temperature points corresponding to the target sampled label data within the second temperature sub-interval satisfies a preset condition. For example, if the second sampled temperature point is the last point in the second temperature sub-interval, then this sampled label data can be considered as the final state of the second temperature sub-interval. The target label data Yi corresponding to the second temperature sub-interval can then be determined using the following formula:

[0137] Y i =Y i,interp (λ) (9)

[0138] After determining the target input data corresponding to the first temperature range and the target label data corresponding to the second temperature range, the server can use the target input data and the target label data as target sample data within the first temperature range and the second temperature sub-range corresponding to the first temperature sub-range.

[0139] In one embodiment, refer to Figure 6 This provides an exemplary data acquisition method that can be applied to... Figure 1 The implementation environment shown.

[0140] Step 601: Obtain multiple initial sample data.

[0141] The initial sample data includes an input data sequence and a corresponding label data sequence. The input data sequence corresponds to the first temperature range, and the label data sequence corresponds to the second temperature range.

[0142] Step 602: For an initial sample data, determine multiple first temperature points based on the sample expansion factor and the first interval conversion condition.

[0143] Step 603: Determine multiple second temperature points based on the sample expansion factor and the second interval conversion conditions.

[0144] Step 604: Obtain the first starting point corresponding to the first temperature range and the second starting point corresponding to the second temperature range.

[0145] Step 605: For a first temperature point, determine the temperature range between the first starting point and the first temperature point as a first temperature sub-range.

[0146] Step 606: For a second temperature point, determine the temperature range between the second starting point and the second temperature point as a second temperature sub-range.

[0147] Step 607: For a first temperature sub-interval, determine multiple first sampling temperature points based on the number of first sampling points and the first sampling conversion conditions.

[0148] Each of the first sampling temperature points is located within the first temperature sub-interval.

[0149] Step 608: For the second temperature sub-interval corresponding to the first temperature sub-interval, determine multiple second sampling temperature points based on the number of second sampling points and the second sampling conversion conditions.

[0150] Each of the second sampling temperature points is located within the second temperature sub-interval.

[0151] Step 609: Determine the sampling input data corresponding to each first sampling temperature point based on the input data sequence fragment corresponding to the first temperature sub-interval and the first interpolation condition.

[0152] Step 610: Determine the sampling label data corresponding to each second sampling temperature point based on the label data sequence fragment corresponding to the second temperature sub-interval and the second preset interpolation conditions.

[0153] Step 611: Take the target sampling label data in each sampling label data as the target label data.

[0154] Among them, the order of the second sampling temperature points corresponding to the target sampling label data in the second temperature sub-interval satisfies the preset conditions.

[0155] Step 612: Use each sampled input data as the target input data.

[0156] Step 613: Use the target input data and target label data as target sample data.

[0157] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0158] This application also provides a model training method, referring to... Figure 7 The method includes:

[0159] Step 701: Obtain multiple target sample data using any of the data acquisition methods described in the above embodiments.

[0160] Step 702: Iteratively train the initial model based on the multiple target sample data to obtain the target model.

[0161] The target model is used to determine the label data corresponding to the input data based on the input data.

[0162] Through the data acquisition method in the above embodiments, the server can obtain the expanded target sample data, and then use this target sample data to train the initial model to obtain the target model.

[0163] The initial model can be selected according to the actual application. It can be a machine learning model, a deep learning model, or a combination of different models. In the embodiments of this application, according to the prediction requirements, such as the heat generation power of battery materials or material combinations as input data and the predicted label data as the temperature rise rate, a combination of deep learning convolutional neural networks and artificial neural networks can be selected to establish the correspondence between input data and label data, thereby obtaining the corresponding initial model.

[0164] Before building the initial model, you can first determine the input and output dimensions of the initial model, referring to... Figure 8 The input dimension is the dimension of the input data, and the output dimension is the dimension of the label data.

[0165] In this embodiment of the application, if the input data is the heat generation power of the positive electrode material, the heat generation power of the negative electrode material, the heat generation power of the positive electrode + negative electrode material, the heat generation power of the positive electrode + electrolyte, or the heat generation power of the negative electrode + electrolyte, then the input dimension is 5. If the label data is the temperature rise rate, then the output dimension is 1.

[0166] In one possible implementation, the server can also use the temperature sequence corresponding to the target sample data as input data, in which case the input dimension is the dimension of the input data plus 1.

[0167] After determining the input and output dimensions of the initial model, the server can build the initial model based on the input and output dimensions, the selected model, input data, and label data. The network layers of the initial model can be determined according to the actual application requirements. In this embodiment, the initial model can consist of three convolutional layers (C1, C2, C3), three pooling layers (P1, P2, P3), and three fully connected layers (D1, D2, D3). The order of the network layers of the initial model is C1-P1-C2-P2-C3-P3-D1-D2-D3.

[0168] After determining the network layers of the initial model, the server can also set different network parameters. For example, referring to Table 1, the following parameters can be set for the network layers determined above:

[0169]

[0170] Table 1

[0171] Understandably, the number of network parameters should not exceed the amount of target sample data.

[0172] After the initial model is launched, the server can iteratively train the initial model based on the target sample data.

[0173] In this embodiment, the server can first divide the target sample data into a test set and a training set according to a preset ratio. In this embodiment, the preset ratio can be 90%. The target sample data in the training set is used to train the initial model, while the target sample data in the test set can be used to evaluate the trained model to determine whether the model has converged.

[0174] The server can iteratively train the initial model based on the target sample data in the test set. For each iteration, the training process can be referenced. Figure 9 The server can input the target input data from the target sample data into the model to obtain the predicted label data output by the model. The server can calculate the loss value of this iteration training process based on the preset loss function, the predicted label data, and the target label data, and adjust the network parameters in the model according to the loss value. It can be understood that the loss value in each round needs to gradually decrease with the number of iterations. In the embodiments of this application, it can be referred to Figure 10 This represents the change in loss value with the number of iterations.

[0175] When adjusting network parameter values ​​based on loss values, adjustments such as regularization penalty terms can be added to avoid the impact of erroneous target sample data on the network parameter update process.

[0176] In this embodiment of the application, after the target sample data in the test set has been used to train the model once, an intermediate model can be obtained. At this time, the server can use the target sample data in the test set to verify the intermediate model and determine whether the intermediate model has converged. If it has converged, the intermediate model is determined to be the target model; otherwise, model training continues.

[0177] Regarding the verification process, the server can input the target input data from the test set into the intermediate model to obtain the predicted label data corresponding to each target input data. Then, based on the predicted label data, the target label data corresponding to each target input data, and the loss function, the server calculates the loss value corresponding to each target input data. If the loss value is greater than a preset threshold, the intermediate model is iteratively trained using the target sample data. If the loss value is less than the preset threshold, the intermediate model is determined to have converged, and the intermediate model is determined to be the target model.

[0178] In one possible implementation, five-fold cross-validation can be used to train and evaluate the initial model. The process of training the initial model using five-fold cross-validation can be described as follows: The server divides the training set into five groups and uses these five groups to iteratively train the model. For the target sample data in one group of training sets, the server iteratively trains the model using each target sample data to obtain an intermediate model. At this point, the server can validate the intermediate model using the target sample data in the test set to obtain the loss value corresponding to that group of training sets. The server then continues to iteratively train the intermediate model using the training sets of the other groups, and so on. Once the target sample data in all five groups of training sets has been used to train the model, the server obtains the loss values ​​corresponding to the five groups of training sets. The server can calculate the average of the loss values ​​of the five groups of training sets to obtain the average difference. At this point, the server can also use the intermediate model trained on the five groups of training sets to validate the target sample data in the test set to obtain the corresponding test loss value. Figure 11 If the average difference (left, 0.14) and the test loss (right, 0.134) are similar (the difference is less than the threshold), it can be determined that the intermediate model has converged, and the intermediate model can be used as the target model.

[0179] Reference Figure 12 To process the target input data in a portion of the target sample data using the target model, the resulting predicted label data and corresponding loss values ​​show that the predicted label data is basically consistent with the target label data corresponding to the target input data.

[0180] After obtaining the target model, the server can also use supplementary test data to evaluate the performance of the target model. For example, the server can obtain the second initial sample data obtained from the new experiment, and then use the data acquisition method in the above embodiment to expand the second initial sample data to obtain the second target sample data. The server can use each second target sample data to verify the target model and obtain the performance evaluation result of the target model.

[0181] The results of this process can be referenced. Figure 13It can be seen that, for the newly acquired second target sample data, the target model analyzes the second target input data in the second target sample data, and the result obtained is the second predicted label data corresponding to the second target input data. Figure 13 (Left), in addition, the second loss value corresponding to the second target sample data will also be obtained ( Figure 13 As shown on the right, the target model has a very small error in processing the second target input data and has high prediction accuracy.

[0182] In subsequent processes, the server can also expand the initial sample data obtained from the re-experiment according to the data acquisition method in the above embodiments, and the obtained target sample data can be used to update the target model.

[0183] Based on the same inventive concept, this application also provides a data acquisition apparatus for implementing the data acquisition method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more data acquisition apparatus embodiments provided below can be found in the limitations of the data acquisition method described above, and will not be repeated here.

[0184] In one exemplary embodiment, such as Figure 14 As shown, a data acquisition device is provided, including: an acquisition module 1401, a temperature range extraction module 1402, and a target module 1403, wherein:

[0185] The acquisition module 1401 is used to acquire multiple initial sample data, which include an input data sequence and a label data sequence corresponding to the input data sequence. The input data sequence corresponds to a first temperature range, and the label data sequence corresponds to a second temperature range.

[0186] Temperature range extraction module 1402 is used to extract temperature ranges from a first temperature range and a second temperature range respectively according to a preset sample expansion factor for an initial sample data, so as to obtain multiple first temperature sub-ranges corresponding to the first temperature range and multiple second temperature sub-ranges corresponding to the second temperature range.

[0187] The target module 1403 is used to perform sample augmentation processing on the input data sequence according to multiple first temperature sub-intervals, and to perform sample augmentation processing on the label data sequence according to multiple second temperature sub-intervals, so as to obtain multiple target sample data.

[0188] In one embodiment, the temperature range extraction module 1402 includes:

[0189] The first interval conversion unit is used to determine multiple first temperature points based on the sample augmentation factor and the first interval conversion conditions;

[0190] The second interval conversion unit is used to determine multiple second temperature points based on the sample augmentation factor and the second interval conversion conditions.

[0191] The temperature range extraction unit is used to extract the temperature range of the first temperature range according to each first temperature point to obtain multiple first temperature sub-ranges, and to extract the temperature range of the second temperature range according to each second temperature point to obtain multiple second temperature sub-ranges.

[0192] In one embodiment, the temperature range extraction unit is specifically used to perform:

[0193] Obtain the first starting point corresponding to the first temperature range and the second starting point corresponding to the second temperature range;

[0194] For a given first temperature point, the temperature range between the first starting point and the first temperature point is defined as a first temperature sub-range.

[0195] For a given second temperature point, the temperature range between the second starting point and the second temperature point is defined as a second temperature sub-range.

[0196] In one embodiment, target module 1403 includes:

[0197] The first sampling conversion unit is used to determine multiple first sampling temperature points for a first temperature sub-interval based on the number of first sampling points and the first sampling conversion conditions, wherein each first sampling temperature point is located within the first temperature sub-interval.

[0198] The second sampling conversion unit is used to determine multiple second sampling temperature points for the second temperature sub-interval corresponding to the first temperature sub-interval, based on the number of second sampling points and the second sampling conversion conditions, with each second sampling temperature point located within the second temperature sub-interval.

[0199] The target determination unit is used to determine the target sample data in the first temperature sub-interval and the second temperature sub-interval corresponding to the first temperature sub-interval based on the input data sequence fragments corresponding to each first sampling temperature point, each second sampling temperature point, the first temperature sub-interval, and the label data sequence fragments corresponding to the second temperature sub-interval.

[0200] In one embodiment, the target determination unit is specifically used to perform:

[0201] Based on the input data sequence segment corresponding to the first temperature sub-interval and the first interpolation condition, determine the sampling input data corresponding to each first sampling temperature point;

[0202] Based on the tag data sequence fragments corresponding to the second temperature sub-interval and the second preset interpolation conditions, determine the sampling tag data corresponding to each second sampling temperature point;

[0203] The target sample data corresponding to the first temperature sub-interval is determined based on each sampled input data and each sampled label data.

[0204] In one embodiment, the target determination unit is also used to perform:

[0205] The target sampling label data in each sampling label data is taken as the target label data, and the order of the second sampling temperature points corresponding to the target sampling label data in the second temperature sub-interval satisfies the preset condition.

[0206] Each sampled input data is used as the target input data;

[0207] The target input data and target label data are used as target sample data.

[0208] Each module in the aforementioned data acquisition device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0209] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 15 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database is used to store and retrieve data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a data acquisition method.

[0210] Those skilled in the art will understand that Figure 15 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0211] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0212] Multiple initial sample data are acquired, the initial sample data including an input data sequence and a label data sequence corresponding to the input data sequence, the input data sequence corresponding to a first temperature range, and the label data sequence corresponding to a second temperature range;

[0213] For a given initial sample data, temperature range extraction is performed on the first temperature range and the second temperature range according to a preset sample expansion factor, to obtain multiple first temperature sub-ranges corresponding to the first temperature range and multiple second temperature sub-ranges corresponding to the second temperature range.

[0214] The input data sequence is subjected to sample augmentation processing based on the plurality of first temperature sub-intervals, and the label data sequence is subjected to sample augmentation processing based on the plurality of second temperature sub-intervals to obtain a plurality of target sample data.

[0215] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0216] Based on the sample expansion factor and the first interval conversion condition, multiple first temperature points are determined;

[0217] Based on the sample expansion factor and the second interval conversion condition, multiple second temperature points are determined;

[0218] Based on each of the first temperature points, the first temperature interval is extracted to obtain multiple first temperature sub-intervals, and based on each of the second temperature points, the second temperature interval is extracted to obtain multiple second temperature sub-intervals.

[0219] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0220] Obtain the first starting point corresponding to the first temperature range and the second starting point corresponding to the second temperature range;

[0221] For a given first temperature point, the temperature range between the first starting point and the first temperature point is defined as a first temperature sub-range.

[0222] For a given second temperature point, the temperature range between the second starting point and the second temperature point is defined as a second temperature sub-range.

[0223] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0224] For a given first temperature sub-interval, multiple first sampling temperature points are determined based on the number of first sampling points and the first sampling conversion conditions, with each first sampling temperature point located within the first temperature sub-interval.

[0225] For the second temperature sub-interval corresponding to the first temperature sub-interval, multiple second sampling temperature points are determined based on the number of second sampling points and the second sampling conversion conditions, and each second sampling temperature point is located within the second temperature sub-interval;

[0226] The target sample data within the first temperature sub-interval and the second temperature sub-interval corresponding to the first temperature sub-interval are determined based on each of the first sampling temperature points, each of the second sampling temperature points, the input data sequence fragments corresponding to the first temperature sub-interval, and the tag data sequence fragments corresponding to the second temperature sub-interval.

[0227] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0228] Based on the input data sequence segment corresponding to the first temperature sub-interval and the first interpolation condition, determine the sampling input data corresponding to each of the first sampling temperature points;

[0229] Based on the tag data sequence fragments corresponding to the second temperature sub-interval and the second preset interpolation conditions, determine the sampling tag data corresponding to each of the second sampling temperature points;

[0230] The target sample data corresponding to the first temperature sub-interval is determined based on each of the sampling input data and each of the sampling label data.

[0231] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0232] The target sampling label data in each of the sampling label data is taken as the target label data, and the order of the second sampling temperature points corresponding to the target sampling label data in the second temperature sub-interval satisfies a preset condition.

[0233] Each of the aforementioned sampled input data is used as the target input data;

[0234] The target input data and the target label data are used as the target sample data.

[0235] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0236] Multiple initial sample data are acquired, the initial sample data including an input data sequence and a label data sequence corresponding to the input data sequence, the input data sequence corresponding to a first temperature range, and the label data sequence corresponding to a second temperature range;

[0237] For a given initial sample data, temperature range extraction is performed on the first temperature range and the second temperature range according to a preset sample expansion factor, to obtain multiple first temperature sub-ranges corresponding to the first temperature range and multiple second temperature sub-ranges corresponding to the second temperature range.

[0238] The input data sequence is subjected to sample augmentation processing based on the plurality of first temperature sub-intervals, and the label data sequence is subjected to sample augmentation processing based on the plurality of second temperature sub-intervals to obtain a plurality of target sample data.

[0239] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0240] Based on the sample expansion factor and the first interval conversion condition, multiple first temperature points are determined;

[0241] Based on the sample expansion factor and the second interval conversion condition, multiple second temperature points are determined;

[0242] Based on each of the first temperature points, the first temperature interval is extracted to obtain multiple first temperature sub-intervals, and based on each of the second temperature points, the second temperature interval is extracted to obtain multiple second temperature sub-intervals.

[0243] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0244] Obtain the first starting point corresponding to the first temperature range and the second starting point corresponding to the second temperature range;

[0245] For a given first temperature point, the temperature range between the first starting point and the first temperature point is defined as a first temperature sub-range.

[0246] For a given second temperature point, the temperature range between the second starting point and the second temperature point is defined as a second temperature sub-range.

[0247] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0248] For a given first temperature sub-interval, multiple first sampling temperature points are determined based on the number of first sampling points and the first sampling conversion conditions, with each first sampling temperature point located within the first temperature sub-interval.

[0249] For the second temperature sub-interval corresponding to the first temperature sub-interval, multiple second sampling temperature points are determined based on the number of second sampling points and the second sampling conversion conditions, and each second sampling temperature point is located within the second temperature sub-interval;

[0250] The target sample data within the first temperature sub-interval and the second temperature sub-interval corresponding to the first temperature sub-interval are determined based on each of the first sampling temperature points, each of the second sampling temperature points, the input data sequence fragments corresponding to the first temperature sub-interval, and the tag data sequence fragments corresponding to the second temperature sub-interval.

[0251] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0252] Based on the input data sequence segment corresponding to the first temperature sub-interval and the first interpolation condition, determine the sampling input data corresponding to each of the first sampling temperature points;

[0253] Based on the tag data sequence fragments corresponding to the second temperature sub-interval and the second preset interpolation conditions, determine the sampling tag data corresponding to each of the second sampling temperature points;

[0254] The target sample data corresponding to the first temperature sub-interval is determined based on each of the sampling input data and each of the sampling label data.

[0255] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0256] The target sampling label data in each of the sampling label data is taken as the target label data, and the order of the second sampling temperature points corresponding to the target sampling label data in the second temperature sub-interval satisfies a preset condition.

[0257] Each of the aforementioned sampled input data is used as the target input data;

[0258] The target input data and the target label data are used as the target sample data.

[0259] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0260] Multiple initial sample data are acquired, the initial sample data including an input data sequence and a label data sequence corresponding to the input data sequence, the input data sequence corresponding to a first temperature range, and the label data sequence corresponding to a second temperature range;

[0261] For a given initial sample data, temperature range extraction is performed on the first temperature range and the second temperature range according to a preset sample expansion factor, to obtain multiple first temperature sub-ranges corresponding to the first temperature range and multiple second temperature sub-ranges corresponding to the second temperature range.

[0262] The input data sequence is subjected to sample augmentation processing based on the plurality of first temperature sub-intervals, and the label data sequence is subjected to sample augmentation processing based on the plurality of second temperature sub-intervals to obtain a plurality of target sample data.

[0263] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0264] Based on the sample expansion factor and the first interval conversion condition, multiple first temperature points are determined;

[0265] Based on the sample expansion factor and the second interval conversion condition, multiple second temperature points are determined;

[0266] Based on each of the first temperature points, the first temperature interval is extracted to obtain multiple first temperature sub-intervals, and based on each of the second temperature points, the second temperature interval is extracted to obtain multiple second temperature sub-intervals.

[0267] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0268] Obtain the first starting point corresponding to the first temperature range and the second starting point corresponding to the second temperature range;

[0269] For a given first temperature point, the temperature range between the first starting point and the first temperature point is defined as a first temperature sub-range.

[0270] For a given second temperature point, the temperature range between the second starting point and the second temperature point is defined as a second temperature sub-range.

[0271] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0272] For a given first temperature sub-interval, multiple first sampling temperature points are determined based on the number of first sampling points and the first sampling conversion conditions, with each first sampling temperature point located within the first temperature sub-interval.

[0273] For the second temperature sub-interval corresponding to the first temperature sub-interval, multiple second sampling temperature points are determined based on the number of second sampling points and the second sampling conversion conditions, and each second sampling temperature point is located within the second temperature sub-interval;

[0274] The target sample data within the first temperature sub-interval and the second temperature sub-interval corresponding to the first temperature sub-interval are determined based on each of the first sampling temperature points, each of the second sampling temperature points, the input data sequence fragments corresponding to the first temperature sub-interval, and the tag data sequence fragments corresponding to the second temperature sub-interval.

[0275] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0276] Based on the input data sequence segment corresponding to the first temperature sub-interval and the first interpolation condition, determine the sampling input data corresponding to each of the first sampling temperature points;

[0277] Based on the tag data sequence fragments corresponding to the second temperature sub-interval and the second preset interpolation conditions, determine the sampling tag data corresponding to each of the second sampling temperature points;

[0278] The target sample data corresponding to the first temperature sub-interval is determined based on each of the sampling input data and each of the sampling label data.

[0279] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0280] The target sampling label data in each of the sampling label data is taken as the target label data, and the order of the second sampling temperature points corresponding to the target sampling label data in the second temperature sub-interval satisfies a preset condition.

[0281] Each of the aforementioned sampled input data is used as the target input data;

[0282] The target input data and the target label data are used as the target sample data.

[0283] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0284] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0285] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0286] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A data acquisition method, characterized by, The method comprises: obtaining a plurality of initial sample data, the initial sample data comprising an input data sequence and a label data sequence corresponding to the input data sequence, the input data sequence corresponding to a first temperature interval, and the label data sequence corresponding to a second temperature interval; the initial sample data comprising initial sample data of a battery, the initial sample data being input by a user through an external input device; for one of the initial sample data, performing temperature interval extraction on the first temperature interval and the second temperature interval according to a preset sample expansion multiple, to obtain a plurality of first temperature subintervals corresponding to the first temperature interval and a plurality of second temperature subintervals corresponding to the second temperature interval; segmenting the input data sequence according to each of the first temperature subintervals to obtain a plurality of input data sequence segments corresponding to each of the first temperature subintervals, and segmenting the label data sequence according to each of the second temperature subintervals to obtain a plurality of label data sequence segments corresponding to each of the second temperature subintervals; performing sample expansion processing on each of the input data sequence segments according to the plurality of first temperature subintervals, and performing sample expansion processing on each of the label data sequence segments according to the plurality of second temperature subintervals, to obtain a plurality of target sample data; the target sample data being used for model training.

2. The method of claim 1, wherein, The method comprises: determining a plurality of first temperature points according to the sample expansion multiple and a first interval conversion condition; determining a plurality of second temperature points according to the sample expansion multiple and a second interval conversion condition; performing temperature interval extraction on the first temperature interval according to each of the first temperature points to obtain a plurality of first temperature subintervals, and performing temperature interval extraction on the second temperature interval according to each of the second temperature points to obtain a plurality of second temperature subintervals.

3. The method of claim 2, wherein, The method comprises: obtaining a first starting point corresponding to the first temperature interval and a second starting point corresponding to the second temperature interval; for one of the first temperature points, determining a temperature interval between the first starting point and one of the first temperature points as one of the first temperature subintervals; for one of the second temperature points, determining a temperature interval between the second starting point and one of the second temperature points as one of the second temperature subintervals.

4. The method of claim 1, wherein, The method comprises: performing sample expansion processing on each of the input data sequence segments according to the plurality of first temperature subintervals, and performing sample expansion processing on each of the label data sequence segments according to the plurality of second temperature subintervals, to obtain a plurality of target sample data; the target sample data being used for model training. For one of the first temperature sub-intervals, a plurality of first sampling temperature points are determined according to a first sampling point number and a first sampling conversion condition, each of the first sampling temperature points being in the first temperature sub-interval; For a second temperature sub-interval corresponding to the first temperature sub-interval, a plurality of second sampling temperature points are determined according to a second sampling point number and a second sampling conversion condition, each of the second sampling temperature points being in the second temperature sub-interval; Target sample data in the first temperature sub-interval and the second temperature sub-interval corresponding to the first temperature sub-interval are determined according to each of the first sampling temperature points, each of the second sampling temperature points, the input data sequence segment corresponding to the first temperature sub-interval, and the label data sequence segment corresponding to the second temperature sub-interval.

5. The method of claim 4, wherein, The determination of the target sample data in the first temperature sub-interval according to each of the first sampling temperature points, each of the second sampling temperature points, the input data sequence segment corresponding to the first temperature sub-interval, and the label data sequence segment corresponding to the second temperature sub-interval includes: Sample input data corresponding to each of the first sampling temperature points is determined according to the input data sequence segment corresponding to the first temperature sub-interval and a first interpolation condition; Sample label data corresponding to each of the second sampling temperature points is determined according to the label data sequence segment corresponding to the second temperature sub-interval and a second preset interpolation condition; The target sample data corresponding to the first temperature sub-interval is determined according to each of the sample input data and each of the sample label data.

6. The method of claim 5, wherein, The determination of the target sample data corresponding to the first temperature sub-interval according to each of the sample input data and each of the sample label data includes: A target sample label data in each of the sample label data is taken as target label data, an order of a second sampling temperature point corresponding to the target sample label data in the second temperature sub-interval satisfying a preset condition; Each of the sample input data is taken as target input data; The target input data and the target label data are taken as the target sample data.

7. A model training method, comprising: The method includes: A plurality of target sample data are obtained by using any one of the data obtaining methods in claims 1-6; An initial model is iteratively trained according to the plurality of target sample data to obtain a target model, the target model being used to determine label data corresponding to input data according to the input data.

8. A data acquisition device, characterized by The device includes: An obtaining module is configured to obtain a plurality of initial sample data, the initial sample data including an input data sequence and a label data sequence corresponding to the input data sequence, the input data sequence corresponding to a first temperature interval, and the label data sequence corresponding to a second temperature interval; the initial sample data including initial sample data of a battery, the initial sample data being input by a user through an external input device; The temperature interval extraction module is configured to, for one of the initial sample data, perform temperature interval extraction on the first temperature interval and the second temperature interval respectively according to a preset sample expansion multiple, to obtain a plurality of first temperature subintervals corresponding to the first temperature interval and a plurality of second temperature subintervals corresponding to the second temperature interval; perform segmentation on the input data sequence according to each of the first temperature subintervals to obtain a plurality of input data sequence segments corresponding to each of the first temperature subintervals, and perform segmentation on the label data sequence according to each of the second temperature subintervals to obtain a plurality of label data sequence segments corresponding to each of the second temperature subintervals; The target module is configured to perform sample expansion processing on each of the input data sequence segments according to the plurality of first temperature subintervals, and perform sample expansion processing on each of the label data sequence segments according to the plurality of second temperature subintervals, to obtain a plurality of target sample data; the target sample data is used for model training. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to implement the steps of the method in any one of claims 1 to 6.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

11. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6. The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

Images