Biological information classification method, device, storage medium and electronic device

Abstract

The present application discloses a biological information classification method, device, storage medium and electronic device, which belongs to the field of biological information recognition, wherein the biological information classification method includes: obtaining biological images to be classified; inputting the biological images to be classified into a trained machine learning model to obtain classification information of the biological images to be classified, and the trained machine learning model is obtained by optimizing the parameters of the machine learning model using a particle swarm optimization algorithm with positive and negative domain inertia weights. The method uses a trained machine learning model to classify the biological information of biological images, which saves labor costs and greatly improves the classification speed. The trained machine learning model is obtained by optimizing the parameters of the machine learning model using a particle swarm optimization algorithm with positive and negative domain inertia weights, and the classification accuracy is higher than that of traditional models.

Description

Technical Field

[0001] The present application belongs to the field of biometric information identification technology, and specifically relates to a biometric information classification method, device, storage medium and electronic device. Background Art

[0002] Biological information is information that reflects the state and mode of biological movement.

[0003] At present, the classification of images containing biological information is all done by manual recognition and classification, which requires the recognition personnel to have high professional knowledge, and the classification speed is slow, and the labor and time costs are very high. Summary of the invention

[0004] The purpose of this application is to provide a biological information classification method, device, storage medium and electronic device to solve the problem of high cost of existing classification methods.

[0005] According to a first aspect of an embodiment of the present application, a method for classifying biological information is provided, and the method may include:

[0006] Get the biological images to be classified;

[0007] The biological image to be classified is input into a trained machine learning model to obtain classification information of the biological image to be classified. The trained machine learning model is obtained by optimizing the parameters of the machine learning model using a particle swarm optimization algorithm with positive and negative domain inertia weights.

[0008] In some optional embodiments of the present application, the speed update formula of the particle swarm optimization algorithm with positive and negative domain inertia weights is:

[0009] v id (t+1)=(-1) t w(t)v id (t)+c 1 r 1 [pbest i (t)-x id (t)]+c 2 r 2 [gbest(t)-x id (t)];

[0010] Among them, v id (t+1) is the flight speed of particle i at t+1 in the dth dimension, v id (t)) is the velocity of the particle in the tth generation, w(t) is the inertia weight, pbest i is the optimal value of particle i, gbest is the global optimal value of the population, c 1 and c 2 is the learning factor, c1 =c 2 =2, r 1 and r 2 A random number in [0,1].

[0011] In some optional embodiments of the present application, the position update formula of the particle swarm optimization algorithm with positive and negative domain inertia weights is:

[0012] x id (t+1)=x id (t)+v id (t+1);

[0013] Among them, x id (t) is the particle position of the tth generation; x id (t+1) is the position of the particle in the t+1th generation.

[0014] In some optional embodiments of the present application, the inertia weight of the particle swarm optimization algorithm with positive and negative domain inertia weights ranges from -1.2 to +1.2.

[0015] In some optional embodiments of the present application, the trained machine learning model is obtained by training using the following method:

[0016] Get a collection of images with biological information;

[0017] Marking each picture in the picture set according to the classification of biological information to obtain a training picture set;

[0018] The machine learning model is trained using the training picture set, and the machine learning model is optimized using the particle swarm optimization algorithm with positive and negative domain inertia weights to obtain the trained machine learning model.

[0019] According to a second aspect of an embodiment of the present application, a biological information classification device is provided, which may include:

[0020] An acquisition module is used to acquire biological images to be classified;

[0021] The classification module is used to input the biological image to be classified into a trained machine learning model to obtain classification information of the biological image to be classified. The trained machine learning model is obtained by optimizing the parameters of the machine learning model using a particle swarm optimization algorithm with positive and negative domain inertia weights.

[0022] According to a third aspect of an embodiment of the present application, an electronic device is provided, which may include:

[0023] processor;

[0024] a memory for storing processor-executable instructions;

[0025] The processor is configured to execute instructions to implement the biological information classification method as shown in any one of the embodiments of the first aspect.

[0026] According to a fourth aspect of an embodiment of the present application, a storage medium is provided. When instructions in the storage medium are executed by a processor of an information processing device or a server, the information processing device or the server implements a method for classifying biological information as shown in any one of the embodiments of the first aspect.

[0027] According to a fifth aspect of the embodiments of the present application, a chip is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement a biological information classification method as shown in any one of the embodiments of the first aspect.

[0028] The above technical solution of the present application has the following beneficial technical effects:

[0029] The method of the embodiment of the present application obtains biological images to be classified; the biological images to be classified are input into a trained machine learning model to obtain classification information of the biological images to be classified. The method uses the trained machine learning model to classify the biological information of the biological images, which saves labor costs and greatly improves the classification speed. The trained machine learning model is obtained by optimizing the parameters of the machine learning model using a particle swarm optimization algorithm with positive and negative domain inertia weights, and the classification accuracy is higher than that of traditional models. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is a schematic flow chart of a classification method of biological information in an exemplary embodiment of the present application;

[0031] Figure 2 is a schematic diagram of the structure of a biological information classification device in an exemplary embodiment of the present application;

[0032] Figure 3 is a schematic structural diagram of an electronic device in an exemplary embodiment of the present application;

[0033] Figure 4 It is a schematic diagram of the hardware structure of an electronic device in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with specific implementations and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present application. In addition, in the following description, the description of known structures and technologies is omitted to avoid unnecessary confusion of the concepts of the present application.

[0035] The accompanying drawings show schematic diagrams of layer structures according to embodiments of the present application. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clarity. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0036] Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0037] In the description of the present application, it should be noted that the terms "first", "second" and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0038] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0039] The following describes in detail the biological information classification method provided by the embodiment of the present application through specific embodiments and application scenarios in conjunction with the accompanying drawings.

[0040] like Figure 1 As shown, according to a first aspect of an embodiment of the present application, a method for classifying biological information is provided, and the method may include:

[0041] S110: Obtaining biological images to be classified;

[0042] S120: Inputting the biological image to be classified into a trained machine learning model to obtain classification information of the biological image to be classified, wherein the trained machine learning model is obtained by optimizing the parameters of the machine learning model using a particle swarm optimization algorithm with positive and negative domain inertia weights.

[0043] The method of this embodiment uses a trained machine learning model to classify the biological information of biological images, which saves labor costs and greatly improves the classification speed. The trained machine learning model is obtained by optimizing the parameters of the machine learning model using a particle swarm optimization algorithm with positive and negative domain inertia weights, and the classification accuracy is higher than that of traditional models.

[0044] In order to describe the embodiment of the present application more clearly, the above steps are described below respectively:

[0045] First, step S110 is to obtain biological images to be classified.

[0046] In this step, the biological images to be classified may be images with people, and the images with people may have specific features corresponding to them, and the features may include gender features, movement state features, physiological state features, etc.

[0047] Next is step S120: inputting the biological image to be classified into the trained machine learning model to obtain classification information of the biological image to be classified, and the trained machine learning model is obtained by optimizing the parameters of the machine learning model using a particle swarm optimization algorithm with positive and negative domain inertia weights.

[0048] The trained machine learning model in this step is obtained by optimizing the parameters of the machine learning model using a particle swarm optimization algorithm with positive and negative domain inertia weights. The inertia weight of the particle swarm optimization algorithm with positive and negative domain inertia weights alternates between the positive domain interval (0, 1.2) and the negative domain interval (-1.2, 0). The particle swarm optimization algorithm with positive and negative domain inertia weights increases the search range of particles, thereby expanding the optimization range of particles, such as Figure 2 As shown, t represents the number of iterations; the inertia weight of alternating oscillation in the positive and negative domains can be expressed as:

[0049] PNoaIW=(-1) t+1 w(t);

[0050] When the number of iterations t is an odd number (t=1, 3, 5, ...), PNoaIW=PIW>0, and when the number of iterations t is an even number (t=2, 4, 6, ...), PNoaIW=-PIW<0. In other words, for PNoaIW, at each iteration, the particle's flight direction is opposite, alternating between the positive and negative domains, so that the particle's flight distance is much greater than flying only in the positive domain. The increase in particle flight distance makes the particle's updated position farther from the position before the update, which is equivalent to expanding the particle's search range and enhancing the particle's global development ability, which is conducive to preventing particles from prematurely maturing and falling into local optimality, and improving the PSO algorithm's ability to obtain the global optimal solution.

[0051] In some optional embodiments of the present application, the update formula of the particle swarm optimization algorithm with positive and negative domain inertia weights is:

[0052] v id (t+1)=(-1) t w(t)v id (t)+c 1 r 1 [pbest i (t)-x id (t)]+c 2 r 2 [gbest(t)-x id (t)];

[0053] Among them, v id (t+1) is the flight speed of particle i at t+1 in the dth dimension, v id (t)) is the velocity of the particle in the tth generation, w(t) is the inertia weight, pbest i is the optimal value of particle i, gbest is the global optimal value of the population, c 1 and c 2 is the learning factor, c 1 =c 2 =2, r 1 and r 2 A random number in [0, 1].

[0054] In some optional embodiments of the present application, the position update formula of the particle swarm optimization algorithm with positive and negative domain inertia weights is:

[0055] x id (t+1)=x id (t)+v id (t+1);

[0056] Among them, x id (t) is the particle position of the tth generation; x id (t+1) is the position of the particle in the t+1th generation.

[0057] In some optional embodiments of the present application, the inertia weight of the particle swarm optimization algorithm with positive and negative domain inertia weights ranges from -1.2 to +1.2.

[0058] In some optional embodiments of the present application, the trained machine learning model is obtained by training using the following method:

[0059] Get a collection of images with biological information;

[0060] Marking each picture in the picture set according to the classification of biological information to obtain a training picture set;

[0061] The machine learning model is trained using the training picture set, and the machine learning model is optimized using the particle swarm optimization algorithm with positive and negative domain inertia weights to obtain the trained machine learning model.

[0062] In order to verify the optimization capability of the inertia weight of the positive and negative domain alternating oscillation in the above embodiment, the CEC2014 test function is used here.

[0063] The CEC2014 test functions include 30 functions, which are divided into four types: 3 unimodal functions, 1 ~f 3 ; 13 Simple Multimodal Functions, f 4 ~f 16 ; 6 hybrid functions, f 17 ~f 22 ; 8 composition functions, f 23 ~f 30 .

[0064] The velocity update formula of the positive domain inertia weight is:

[0065] v id (t+1)=w(t)v id (t)+r 1 [pbest id (t)-x ij (t)]+c 2 r 2 [gbest d (t)-x id (t)];

[0066] The velocity update formula of the negative domain inertia weight is:

[0067] v id (t+1)=-w(t)v id (t)+r 1 [pbest id (t)-x ij (t)]+c 2 r 2 [gbest d (t)-x id (t)];

[0068] The velocity update formula of the alternating inertia weight in the positive and negative domains is:

[0069] v id (t+1)=(-1) t w(t)v id (t)+r 1 [pbest id (t)-x ij (t)]+c 2 r 2 [gbest d (t)-x id (t)];

[0070] The above position update formula is the same:

[0071] x id (t+1)=x id (t)+v id (t+1);

[0072] Analysis of PSO optimization performance based on PNoaIW strategy: per(>), per(>20%) and per(=) respectively represent the proportion of the number of test functions improved by the PNoaIW strategy optimization performance, the number of test functions improved by more than 20% and the number of test functions with the same optimization capability to the total number of test functions.

[0073] In addition, the PNoaIW strategy improves the optimization ability of PSO mainly in single-peak functions, simple multi-peak functions and hybrid functions, but does not show outstanding advantages in composition functions. On the other hand, although the PNoaIW strategy also shows certain advantages in the adaptive weight algorithm, the improvement is limited compared with the random and time-varying inertia weights (inertia weights change with the number of iterations). This is because in the adaptive weight algorithm, the change of inertia weight is closely related to the current adaptive value, and the change of inertia weight reflects the change of particle information, which makes the adaptive inertia weight itself have a greater advantage in the optimization ability.

[0074] In order to test the effect of particle swarm optimization algorithm with different inertia weight strategies in practical applications, the particle swarm optimization algorithm is applied to the optimization of classification model parameters in the embodiment of the present application.

[0075] In the embodiment of the present application, an extreme learning machine (KELM) model with an RBF kernel function is used to classify 10 data sets from UCI, and three optimization strategies, PSO with PNoaIW, PSO with PIW and PSO with NIW, are used to optimize the classification model parameters (regularization coefficient and RBF kernel parameter).

[0076] Since the advantages of the positive and negative oscillation inertia weight strategy in the adaptive type are not prominent enough, we selected AdIW-PSO+ (positive domain), AdIW-PSO- (negative domain) and AdIW-PSO± (positive and negative domain) with inertia weight as adaptive type for verification.

[0077] During the testing process, a ten-fold crossover operation was used and the number of iterations was set to 100.

[0078] The classification results of the model optimized using positive and negative oscillating inertia weight PSO (AdIW-PSO±) are better than those in the positive domain (AdIW-PSO+) and the negative domain (AdIW-PSO-), indicating that the positive and negative oscillating inertia weight PSO optimization algorithm is effective.

[0079] In order to improve the particle optimization capability, the embodiment of the present application expands the value range of the inertia weight from the positive domain (0, 1.2) to the negative domain (-1.2, 0), forming a value interval from -1.2 to 1.2, and makes the value of the inertia weight oscillate alternately in the positive and negative domains, that is, the positive and negative domain alternating oscillation inertia weight (PNoaIW).

[0080] The optimization test was conducted using the CEC2014 test function and the actual classification model parameters. The results show that the optimization ability of the inertia weight (PIW) that varies in the positive domain and the inertia weight (NIW) that varies in the negative domain depends on the inertia weight algorithm used. However, compared with both PIW and NIW, the optimization ability based on PNoaIW has been significantly improved, especially the three types of functions, Unimodal, Simple Multimodal and Hybrid, are more prominent in the improvement ability of random and time-varying inertia weight algorithms.

[0081] Exemplarily, using the method of the embodiment of the present application, a kernel extreme learning machine classifier (KELM) is used.

[0082] For biological information classification, biological information classification includes: diabetes, liver disease, Parkinson's disease, and the image data to be classified comes from the UCI database. The classification results are shown in Table 1.

[0083] Table 1

[0084]

[0085] From the above embodiments, it can be seen that the main reason why the PNoaIW strategy improves the performance of the PSO algorithm is that, in each iteration, PNoaIW increases the flight speed and flight distance of the particles. In this way, on the one hand, the increase in flight distance increases the search range of the particles, which is beneficial to the global development of the particles, thereby preventing the particles from being premature and falling into the local optimum; on the other hand, the increase in flight distance also allows particles to have more opportunities to explore the neighboring positions of the historically searched area. As the iteration continues, the search density of the particles increases, which is equivalent to improving the fine search ability of the particles. Therefore, it can be said that for the PSO algorithm using the PNoaIW strategy, the increase in the search range and the increase in the search density work together to improve the particle's optimization ability, thereby improving the optimization performance of the PSO algorithm.

[0086] It should be noted that the execution subject of the biological information classification method provided in the embodiment of the present application may be a biological information classification device, or a control module in the biological information classification device for executing the biological information classification method. In the embodiment of the present application, the biological information classification device executing the biological information classification method is taken as an example to illustrate the biological information classification device provided in the embodiment of the present application.

[0087] like Figure 2 As shown, in a second aspect of the embodiment of the present application, a biological information classification device is provided, and the device may include:

[0088] An acquisition module 210 is used to acquire biological images to be classified;

[0089] The classification module 220 is used to input the biological image to be classified into a trained machine learning model to obtain classification information of the biological image to be classified. The trained machine learning model is obtained by optimizing the parameters of the machine learning model using a particle swarm optimization algorithm with positive and negative domain inertia weights.

[0090] The device of this embodiment uses a trained machine learning model to classify the biological information of biological images, which saves labor costs and greatly improves the classification speed. The trained machine learning model is obtained by optimizing the parameters of the machine learning model using a particle swarm optimization algorithm with positive and negative domain inertia weights, and the classification accuracy is higher than that of traditional models.

[0091] The biometric information classification device in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. The non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0092] The biological information classification device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0093] The biological information classification device provided in the embodiment of the present application can achieve Figure 1 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0094] Alternatively, if Figure 3 As shown, the embodiment of the present application also provides an electronic device 300, including a processor 301, a memory 302, and a program or instruction stored in the memory 302 and executable on the processor 301. When the program or instruction is executed by the processor 301, each process of the above-mentioned biological information classification method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0095] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0096] Figure 4 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.

[0097] The electronic device 400 includes but is not limited to components such as a radio frequency unit 401 , a network module 402 , an audio output unit 403 , an input unit 404 , a sensor 405 , a display unit 406 , a user input unit 407 , an interface unit 408 , a memory 409 , and a processor 410 .

[0098] Those skilled in the art will appreciate that the electronic device 400 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 410 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Figure 4 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0099] It should be understood that in the embodiment of the present application, the input unit 404 may include a graphics processor (GPU) 4041 and a microphone 4042, and the graphics processor 4041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 406 may include a display panel 4061, and the display panel 4061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 407 includes a touch panel 4071 and other input devices 4072. The touch panel 4071 is also called a touch screen. The touch panel 4071 may include two parts: a touch detection device and a touch controller. Other input devices 4072 may include, but are not limited to, a physical keyboard, a function key (such as a volume control button, a switch button, etc.), a trackball, a mouse, and a joystick, which will not be repeated here. The memory 409 may be used to store software programs and various data, including but not limited to applications and operating systems. The processor 410 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and applications, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 410.

[0100] The embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned biological information classification method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0101] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0102] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned biological information classification method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0103] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0104] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0105] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0106] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A biological information classification method, characterized in that: include: Get the biological images to be classified; Inputting the biological image to be classified into a trained machine learning model to obtain classification information of the biological image to be classified, wherein the trained machine learning model is obtained by optimizing the parameters of the machine learning model using a particle swarm optimization algorithm with positive and negative domain inertia weights; The velocity update formula of the particle swarm optimization algorithm with positive and negative domain inertia weights is: v id (t+1)=(-1) t w(t)v id (t)+c1r1[pbest i (t)-x id (t)]+c2r2[gbest(t)-x id (t)]; Among them, v id (t+1) is the flight speed of particle i at t+1 in the dth dimension, v id (t) is the velocity of the particle in the tth generation, w(t) is the inertia weight, pbest i is the optimal value of particle i, gbest is the global optimal value of the population, c1 and c2 are learning factors, c1=c2=2, r1 and r2 are random numbers in [0,1]; xid(t) is the position of the particle in the tth generation; Among them, the inertia weight alternates between the positive domain interval (0,1.2) and the negative domain interval (-1.2,0).

2. The biological information classification method according to claim 1, characterized in that: The position update formula of the particle swarm optimization algorithm with positive and negative domain inertia weights is: x id (t+1)=x id (t)+v id (t+1); Among them, x id (t+1) is the position of the particle in the t+1th generation.

3. The biological information classification method according to claim 1, characterized in that: The trained machine learning model is obtained by training using the following method: Get a collection of images with biological information; Marking each picture in the picture set according to the classification of biological information to obtain a training picture set; The machine learning model is trained using the training picture set, and the machine learning model is optimized using the particle swarm optimization algorithm with positive and negative domain inertia weights to obtain the trained machine learning model.

4. A biological information classification device, characterized in that: A method for classifying biological information according to any one of claims 1 to 3, comprising: An acquisition module is used to acquire biological images to be classified; The classification module is used to input the biological image to be classified into a trained machine learning model to obtain classification information of the biological image to be classified. The trained machine learning model is obtained by optimizing the parameters of the machine learning model using a particle swarm optimization algorithm with positive and negative domain inertia weights.

5. An electronic device, characterized in that: include: The method comprises a processor, a memory and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the biological information classification method as described in any one of claims 1 to 3.

6. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the biological information classification method according to any one of claims 1 to 3 are implemented.

7. A chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the steps of the biological information classification method according to any one of claims 1 to 3.

Images