Intelligent terminal reminding method, electronic device and computer readable storage medium

Abstract

The application discloses a kind of intelligent terminal reminding method, electronic equipment and computer readable storage medium, the intelligent terminal reminding method includes: the first image data of target person is collected, the mental state of the target person is predicted based on the first image data;Collect the floating image set in the preset period, and the environmental information in the preset period;Each floating image in the floating image set is carried out feature sampling, and the first floating image feature sequence is obtained;The fish eating state of target area is predicted based on the first floating image feature sequence and the environmental information, and the target area includes the vertical projection area of the floating;In the fish eating state indicates that the probability of fish eating in the target area is lower than the first preset threshold, and the mental state indicates that the target person is lower than the second threshold to the fishing interest, the reminding message is output to the user terminal under the condition that the fishing interest is lower than the second threshold.The present application can save the time of angler.

Description

Technical Field

[0001] This invention belongs to the field of electronic device technology, and particularly relates to a smart terminal reminder method, electronic device, and computer-readable storage medium. Background Technology

[0002] Fishing is becoming increasingly popular, with the number of anglers growing rapidly in recent years, and fishing-related web traffic is also accounting for a significant portion of online activity. As fishing-related web traffic increases, more and more people are carrying various equipment while fishing, such as recording devices. However, these devices only record the fishing activity and cannot assist the angler. This makes it difficult for novice anglers to judge fish behavior, leading to wasted time for some anglers. Summary of the Invention

[0003] This invention provides a smart terminal reminder method, an electronic device, and a computer-readable storage medium to address the problem of anglers easily wasting time.

[0004] This invention provides a smart terminal reminder method, which is applied to an electronic device, wherein the electronic device is communicatively connected to a user terminal, and includes:

[0005] Collect first image data of the target person, and predict the mental state of the target person based on the first image data;

[0006] Collect a set of floating images within a preset time period, as well as environmental information within the preset time period. The duration of the preset time period exceeds a preset duration. The environmental information includes at least one of the following: weather information and water surface image information.

[0007] Feature sampling is performed on each float image in the float image set to obtain a first float image feature sequence;

[0008] Based on the first float image feature sequence and the environmental information, the feeding status of fish in the target area is predicted, and the target area includes the vertical projection area of ​​the float.

[0009] When the fish feeding state indicates that the probability of fish feeding in the target area is lower than a first preset threshold, and the mental state indicates that the target person's interest in fishing is lower than a second threshold, a reminder message is output to the user terminal. The reminder message is used to remind the target person that they cannot catch fish in the target area for a short period of time.

[0010] The present invention also provides an electronic device, comprising:

[0011] The first prediction unit is used to collect first image data of the target person and predict the mental state of the target person based on the first image data.

[0012] The first acquisition unit is used to acquire a set of floating images within a preset time period, as well as environmental information within the preset time period. The duration of the preset time period exceeds a preset duration. The environmental information includes at least one of the following: weather information and water surface image information.

[0013] A sampling unit is used to perform feature sampling on each float image in the float image set to obtain a first float image feature sequence;

[0014] The second prediction unit is used to predict the feeding status of fish in the target area based on the first float image feature sequence and the environmental information, wherein the target area includes the vertical projection area of ​​the float.

[0015] The reminder unit is used to output a reminder message to the user terminal when the fish feeding state indicates that the probability of fish feeding in the target area is lower than a first preset threshold, and the mental state indicates that the target person's interest in fishing is lower than a second threshold. The reminder message is used to remind the target person that they cannot catch fish in the target area for a short period of time.

[0016] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that the program, when executed by a processor, implements the steps in the smart terminal reminder method.

[0017] In this invention, first image data of a target person is collected, and the target person's mental state is predicted based on the first image data; a set of float images within a preset time period and environmental information within the preset time period are collected, the preset time period being longer than a preset duration, and the environmental information including at least one of the following: weather information and water surface image information; feature sampling is performed on each float image in the float image set to obtain a first float image feature sequence; the feeding state of fish in a target area is predicted based on the first float image feature sequence and the environmental information, the target area including the vertical projection area of ​​the float; when the feeding state indicates that the probability of fish feeding in the target area is lower than a first preset threshold, and the mental state indicates that the target person's interest in fishing is lower than a second threshold, a reminder message is output to the user terminal, the reminder message being used to remind the target person that they cannot catch fish in the target area for a short period of time. In this way, the reminder message can effectively remind anglers that they cannot catch fish in the target area for a short period of time, avoiding wasting time without catching fish, thus saving anglers' time. Attached Figure Description

[0018] Figure 1 This is a flowchart of a smart terminal reminder method provided in an embodiment of the present invention;

[0019] Figure 2 This is a schematic diagram of the structure of a neural network model provided in an embodiment of the present invention;

[0020] Figure 3 This is a structural diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0022] Figure 1 This is a flowchart of a smart terminal reminder method provided in an embodiment of the present invention, such as... Figure 1 The following are included:

[0023] Step 101: Collect first image data of the target person, and predict the mental state of the target person based on the first image data;

[0024] Step 102: Collect a set of floating images within a preset time period, as well as environmental information within the preset time period. The duration of the preset time period exceeds a preset duration. The environmental information includes at least one of the following: weather information and water surface image information.

[0025] Step 103: Perform feature sampling on each float image in the float image set to obtain the first float image feature sequence;

[0026] Step 104: Based on the first float image feature sequence and the environmental information, predict the feeding status of fish in the target area, wherein the target area includes the vertical projection area of ​​the float;

[0027] Step 105: When the fish feeding state indicates that the probability of fish feeding in the target area is lower than a first preset threshold, and the mental state indicates that the target person's interest in fishing is lower than a second threshold, a reminder message is output to the user terminal. The reminder message is used to remind the target person that they cannot catch fish in the target area for a short period of time.

[0028] The aforementioned electronic device may be a device with a shooting function installed on a support, a device with a shooting function installed on a fishing box, or a device with a shooting function arranged on a smart fishing float.

[0029] The mental state of the target person mentioned above could be their enthusiasm for fishing.

[0030] The above-mentioned feeding state of fish can be the likelihood of fish feeding, the desire of fish to feed, or the probability of fish feeding.

[0031] The aforementioned reminder message can be sent to the user terminal via telephone or audio call, so that the user can receive the reminder message in a timely manner even without checking the phone.

[0032] Once users receive the above reminder message, they will know that they will not be able to catch fish in the short term, and will then go home or go fishing elsewhere to save their time.

[0033] In this invention, a reminder message can effectively alert anglers that fish cannot be caught in the target area for a short period of time, thus avoiding wasting time and saving anglers' time.

[0034] This invention can effectively remind some fishing novices, thus saving them time.

[0035] In some implementations, predicting the feeding status of fish in the target area based on the first float image feature sequence and the environmental information includes:

[0036] The feature sequence of the floating image is convolved to obtain the convolutional sequence of floating image features. The convolutional sequence of floating image features is then normalized to obtain the normalized sequence of floating image features. The activation weight coefficient of each feature point in the normalized sequence of floating image features is calculated. Each feature point in the normalized sequence of floating image features is multiplied by the activation weight coefficient of that feature point to obtain the second floating image feature sequence.

[0037] The feeding status of fish in the target area is predicted based on the feature sequence of the second float image and the environmental information.

[0038] like Figure 2As shown, in this embodiment, the feeding state of fish in a target area can be predicted using a neural network model including a convolutional layer 201, a normalization layer 202, an activation function layer 203, and a fully connected layer 204. The convolutional layer 201 performs a convolution operation on the feature sequence of the float image to obtain a float image feature convolutional sequence; the normalization layer 202 normalizes the float image feature convolutional sequence to obtain a float image feature normalized sequence; the activation function layer 203 calculates the activation weight coefficient for each feature point in the float image feature normalized sequence, and multiplies each feature point in the float image feature normalized sequence by its activation weight coefficient to obtain a second float image feature sequence; the fully connected layer 204 predicts the feeding state of fish in the target area based on the second float image feature sequence and the environmental information. Furthermore, the aforementioned neural network model is pre-trained or pre-received from other devices for a neural network model related to fish feeding states.

[0039] In this embodiment, the feeding status of fish in the target area can be accurately predicted through the above operations.

[0040] In some implementations, the environmental information includes: weather information and water surface image information;

[0041] The prediction of the feeding status of fish in the target area based on the second float image feature sequence and the environmental information includes:

[0042] Acquire weather information samples, horizontal image information samples, and float image feature sequence samples, as well as target fish feeding tag information. Iteratively train the initial network module based on the weather information samples, horizontal image information samples, float image feature sequence samples, and target fish feeding tag information to obtain a target network module for predicting fish feeding status based on float image feature sequence, weather information, and water surface image information.

[0043] The second float image feature sequence, the weather information, and the water surface image information are input into the target network module for prediction to obtain the feeding status of fish in the target area.

[0044] The target network module mentioned above can be a fully connected layer network, an independent neural network model, or a classification module of a neural network model.

[0045] In this embodiment, since the target network module is iteratively trained on the initial network module based on weather information samples, horizontal image information samples, float image feature sequence samples and target fish feeding tag information, the accuracy of the target network module can be improved, thereby improving the accuracy of the fish feeding status.

[0046] In some implementations, the method further includes:

[0047] The second image data of the target person is collected, the second image data includes the target fish food on the fishing hook of the target person, and the target fish species of the target person is predicted based on the target fish food;

[0048] The prediction of the feeding status of fish in the target area based on the second float image feature sequence and the environmental information includes:

[0049] Based on the second float image feature sequence and the environmental information, predict the feeding status of the target fish species in the target area.

[0050] The above-mentioned prediction of the target fish species of the target person based on the target fish food can be based on the mapping relationship between fish species and fish food established by fishing big data, to predict the target fish species of the target person. For example, the main fish species caught with corn are grass carp, mandarin fish, and common carp, while the main fish species caught with earthworms are crucian carp and yellow catfish.

[0051] Once the target fish species is determined, the feeding habits of the target fish species can be used to more accurately predict the feeding status of the fish, thereby improving the accuracy of the alerts.

[0052] Optionally, the step of predicting the feeding status of the target fish species in the target area based on the second float image feature sequence and the environmental information includes:

[0053] Search a preset database for the feeding information of the target fish species under the weather information. The preset database stores information on multiple fish species in advance, and the information on each fish species includes feeding information under multiple weather conditions.

[0054] Based on the feeding information of the target fish species under the weather information, the feature sequence of the second float image, and the water surface image information, the feeding status of the target fish species in the target area is predicted.

[0055] In this implementation, the feeding status of the target fish species can be further predicted based on the relationship between weather information and the target fish species. This is because different fish species feed differently in different weather conditions. For example, in winter, crucian carp are the main feeders, while other fish species have a lower appetite.

[0056] This implementation method can further improve the accuracy of the fish's feeding status.

[0057] Optionally, predicting the feeding status of the target fish species in the target area based on the feeding information of the target fish species under the weather information, the feature sequence of the second float image, and the water surface image information includes:

[0058] The feature information of the water surface image information is identified, and the feature information is used to represent the state of bubbles on the water surface;

[0059] Based on the bubble state, determine whether the number of bubbles generated on the water surface within a preset time is less than a third preset threshold.

[0060] If the number of bubbles generated on the water surface within a preset time is less than a third preset threshold, and the feeding information indicates that the target fish species' feeding desire is lower than the third preset threshold under the weather information, the second float image feature sequence is used to determine whether the float's movement frequency is gradually decreasing. If the float's movement frequency is gradually decreasing, the feeding status of the target fish species in the target area is predicted.

[0061] In this embodiment, the feeding status of the target fish species in the target area can be predicted only when the number of bubbles generated on the water surface within a preset time is less than a third preset threshold, the feeding information indicates that the target fish species' feeding desire is lower than the third preset threshold under the given weather conditions, and the movement of the float is frequently and gradually decreasing. This allows prediction to be made only under these conditions, thus saving power consumption.

[0062] In some implementations, acquiring first image data of the target person and predicting the target person's mental state based on the first image data includes:

[0063] Collect an image dataset of the target person during the prediction period, wherein each image in the image dataset includes the target person's hand, fishing rod, and float;

[0064] Identify the casting frequency of the target person based on the image dataset;

[0065] Identify the movement of the float each time the target person lifts the rod, the movement including at least one of: the float not changing, the float moving, the float rising, and the float falling;

[0066] Based on the target person's casting frequency and the movement of the float each time the rod is lifted, the target person's mental state is predicted; wherein, when the casting frequency is lower than a fourth threshold, and the proportion of rod lifts during the prediction period in which the float does not change is higher than a fifth threshold, it is determined that the target person's interest in fishing is lower than a second threshold.

[0067] The statement that the casting frequency is lower than the third threshold and the proportion of rod lifts with no change in the float during the prediction period is higher than the fourth threshold can be interpreted as the user casting frequency being very low and the user casting the rod not due to the movement of the float. This indicates that the user is not very interested in fishing at present, thus determining that the target person's interest in fishing is lower than the second threshold.

[0068] When the casting frequency is lower than the third threshold, and the proportion of rod lifts during the predicted period where the float does not change is higher than the fifth threshold, it can be determined that the user's casting is caused by the movement of the float. This indicates that the user is still quite interested in fishing, because each rod lift is done carefully and not randomly.

[0069] When the casting frequency exceeds the third threshold, it indicates that the user is still quite interested in fishing because they are more willing to lift the rod even if the float does not change. The casting frequency indicates that the user is still quite interested in fishing. Even if there are no fish caught, the user is not reminded to discourage their enthusiasm for fishing. For example, if a novice is willing to cast the rod, it indicates that the user is still quite interested in fishing. Even if there are no fish caught, the user is not reminded to discourage their enthusiasm for fishing.

[0070] In this implementation, the above method can effectively remind users to avoid discouraging them from fishing and thus improve the user experience.

[0071] In some implementations, the acquisition of a set of buoy images within a preset time period, and the environmental information within the preset time period, includes:

[0072] Based on the first image data, it is determined whether the target person has caught a fish within a preset time. If the target person has not caught a fish within the preset time, a set of floating images within the preset time period, as well as environmental information within the preset time period, are collected.

[0073] In this implementation, the method can be executed if no fish are caught within a preset time to effectively remind the user, thereby avoiding discouraging the user's enthusiasm for fishing and improving the user experience.

[0074] In this invention, first image data of a target person is collected, and the target person's mental state is predicted based on the first image data; a set of float images within a preset time period and environmental information within the preset time period are collected, the preset time period being longer than a preset duration, and the environmental information including at least one of the following: weather information and water surface image information; feature sampling is performed on each float image in the float image set to obtain a first float image feature sequence; the feeding state of fish in a target area is predicted based on the first float image feature sequence and the environmental information, the target area including the vertical projection area of ​​the float; when the feeding state indicates that the probability of fish feeding in the target area is lower than a first preset threshold, and the mental state indicates that the target person's interest in fishing is lower than a second threshold, a reminder message is output to the user terminal, the reminder message being used to remind the target person that they cannot catch fish in the target area for a short period of time. In this way, the reminder message can effectively remind anglers that they cannot catch fish in the target area for a short period of time, avoiding wasting time without catching fish, thus saving anglers' time.

[0075] Figure 3 This is a structural diagram of an electronic device provided in an embodiment of the present invention, such as... Figure 3 The following are included:

[0076] The first prediction unit 301 is used to collect first image data of the target person and predict the mental state of the target person based on the first image data.

[0077] The first acquisition unit 302 is used to acquire a set of floating images within a preset time period, as well as environmental information within the preset time period. The duration of the preset time period exceeds a preset duration. The environmental information includes at least one of the following: weather information and water surface image information.

[0078] Sampling unit 303 is used to perform feature sampling on each float image in the float image set to obtain a first float image feature sequence;

[0079] The second prediction unit 304 is used to predict the feeding status of fish in a target area based on the first float image feature sequence and the environmental information, wherein the target area includes the vertical projection area of ​​the float.

[0080] The reminder unit 305 is used to output a reminder message to the user terminal when the fish feeding state indicates that the probability of fish feeding in the target area is lower than a first preset threshold, and the mental state indicates that the target person's interest in fishing is lower than a second threshold. The reminder message is used to remind the target person that they cannot catch fish in the target area for a short period of time.

[0081] Optionally, the second prediction unit 304 is used for:

[0082] The feature sequence of the floating image is convolved to obtain the convolutional sequence of floating image features. The convolutional sequence of floating image features is then normalized to obtain the normalized sequence of floating image features. The activation weight coefficient of each feature point in the normalized sequence of floating image features is calculated. Each feature point in the normalized sequence of floating image features is multiplied by the activation weight coefficient of that feature point to obtain the second floating image feature sequence.

[0083] The feeding status of fish in the target area is predicted based on the feature sequence of the second float image and the environmental information.

[0084] Optionally, the environmental information includes: weather information and water surface image information;

[0085] The second prediction unit 304 is used for:

[0086] Acquire weather information samples, horizontal image information samples, and float image feature sequence samples, as well as target fish feeding tag information. Iteratively train the initial network module based on the weather information samples, horizontal image information samples, float image feature sequence samples, and target fish feeding tag information to obtain a target network module for predicting fish feeding status based on float image feature sequence, weather information, and water surface image information.

[0087] The second float image feature sequence, the weather information, and the water surface image information are input into the target network module for prediction to obtain the feeding status of fish in the target area.

[0088] Optionally, the device further includes:

[0089] The second acquisition unit is used to acquire second image data of the target person, the second image data including the target fish food on the fishhook of the target person, and to predict the target fish species of the target person based on the target fish food;

[0090] The second prediction unit 304 is used for:

[0091] Based on the second float image feature sequence and the environmental information, predict the feeding status of the target fish species in the target area.

[0092] Optionally, the second prediction unit 304 is used for:

[0093] Search a preset database for the feeding information of the target fish species under the weather information. The preset database stores information on multiple fish species in advance, and the information on each fish species includes feeding information under multiple weather conditions.

[0094] Based on the feeding information of the target fish species under the weather information, the feature sequence of the second float image, and the water surface image information, the feeding status of the target fish species in the target area is predicted.

[0095] Optionally, the second prediction unit 304 is used for:

[0096] The feature information of the water surface image information is identified, and the feature information is used to represent the state of bubbles on the water surface;

[0097] Based on the bubble state, determine whether the number of bubbles generated on the water surface within a preset time is less than a third preset threshold.

[0098] If the number of bubbles generated on the water surface within a preset time is less than a third preset threshold, and the feeding information indicates that the target fish species' feeding desire is lower than the third preset threshold under the weather information, the second float image feature sequence is used to determine whether the float's movement frequency is gradually decreasing. If the float's movement frequency is gradually decreasing, the feeding status of the target fish species in the target area is predicted.

[0099] Optionally, the first prediction unit 301 is used for:

[0100] Collect an image dataset of the target person during the prediction period, wherein each image in the image dataset includes the target person's hand, fishing rod, and float;

[0101] Identify the casting frequency of the target person based on the image dataset;

[0102] Identify the movement of the float each time the target person lifts the rod, the movement including at least one of: the float not changing, the float moving, the float rising, and the float falling;

[0103] Based on the target person's casting frequency and the movement of the float each time the rod is lifted, the target person's mental state is predicted; wherein, when the casting frequency is lower than a fourth threshold, and the proportion of rod lifts during the prediction period in which the float does not change is higher than a fifth threshold, it is determined that the target person's interest in fishing is lower than a second threshold.

[0104] Optionally, the first acquisition unit 302 is used for:

[0105] Based on the first image data, it is determined whether the target person has caught a fish within a preset time. If the target person has not caught a fish within the preset time, a set of floating images within the preset time period, as well as environmental information within the preset time period, are collected.

[0106] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the smart terminal reminder method provided by the present invention.

[0107] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0108] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0109] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A smart terminal reminder method, characterized in that, Applied to electronic devices, the electronic devices being communicatively connected to user terminals, including: Collect first image data of the target person, and predict the mental state of the target person based on the first image data; Collect a set of floating images within a preset time period, as well as environmental information within the preset time period. The duration of the preset time period exceeds a preset duration. The environmental information includes at least one of the following: weather information and water surface image information. Feature sampling is performed on each float image in the float image set to obtain a first float image feature sequence; Based on the first float image feature sequence and the environmental information, the feeding status of fish in the target area is predicted, and the target area includes the vertical projection area of ​​the float. When the fish feeding state indicates that the probability of fish feeding in the target area is lower than a first preset threshold, and the mental state indicates that the target person's interest in fishing is lower than a second threshold, a reminder message is output to the user terminal. The reminder message is used to remind the target person that they cannot catch fish in the target area for a short period of time.

2. The method according to claim 1, characterized in that, The prediction of the feeding status of fish in the target area based on the feature sequence of the first float image and the environmental information includes: The feature sequence of the floating image is convolved to obtain the convolutional sequence of floating image features. The convolutional sequence of floating image features is then normalized to obtain the normalized sequence of floating image features. The activation weight coefficient of each feature point in the normalized sequence of floating image features is calculated. Each feature point in the normalized sequence of floating image features is multiplied by the activation weight coefficient of that feature point to obtain the second floating image feature sequence. The feeding status of fish in the target area is predicted based on the feature sequence of the second float image and the environmental information.

3. The method according to claim 2, characterized in that, The environmental information includes: weather information and water surface image information; The prediction of the feeding status of fish in the target area based on the second float image feature sequence and the environmental information includes: Acquire weather information samples, water surface image information samples, and float image feature sequence samples, as well as target fish feeding tag information. Based on the weather information samples, water surface image information samples, float image feature sequence samples, and target fish feeding tag information, iteratively train the initial network module to obtain a target network module for predicting the feeding status of fish based on float image feature sequence, weather information, and water surface image information. The second float image feature sequence, the weather information, and the water surface image information are input into the target network module for prediction to obtain the feeding status of fish in the target area.

4. The method according to claim 2, characterized in that, The method further includes: The second image data of the target person is collected, the second image data includes the target fish food on the fishing hook of the target person, and the target fish species of the target person is predicted based on the target fish food; The prediction of the feeding status of fish in the target area based on the second float image feature sequence and the environmental information includes: Based on the second float image feature sequence and the environmental information, predict the feeding status of the target fish species in the target area.

5. The method according to claim 4, characterized in that, The prediction of the feeding status of the target fish species in the target area based on the second float image feature sequence and the environmental information includes: Search a preset database for the feeding information of the target fish species under the weather information. The preset database stores information on multiple fish species in advance, and the information on each fish species includes feeding information under multiple weather conditions. Based on the feeding information of the target fish species under the weather information, the feature sequence of the second float image, and the water surface image information, the feeding status of the target fish species in the target area is predicted.

6. The method according to claim 5, characterized in that, The method of predicting the feeding status of the target fish species in the target area based on the feeding information of the target fish species under the weather information, the feature sequence of the second float image, and the water surface image information includes: The feature information of the water surface image information is identified, and the feature information is used to represent the state of bubbles on the water surface; Based on the bubble state, determine whether the number of bubbles generated on the water surface within a preset time is less than a third preset threshold. If the number of bubbles generated on the water surface within a preset time is less than a third preset threshold, and the feeding information indicates that the target fish species' feeding desire is lower than the third preset threshold under the weather information, the second float image feature sequence is used to determine whether the float's movement frequency is gradually decreasing. If the float's movement frequency is gradually decreasing, the feeding status of the target fish species in the target area is predicted.

7. The method according to any one of claims 1 to 6, characterized in that, The process of collecting first image data of the target person and predicting the mental state of the target person based on the first image data includes: Collect an image dataset of the target person during the prediction period, wherein each image in the image dataset includes the target person's hand, fishing rod, and float; Identify the casting frequency of the target person based on the image dataset; Identify the movement of the float each time the target person lifts the rod, the movement including at least one of: the float not changing, the float moving, the float rising, and the float falling; Based on the target person's casting frequency and the movement of the float each time the rod is lifted, the target person's mental state is predicted; wherein, when the casting frequency is lower than a fourth threshold, and the proportion of rod lifts during the prediction period in which the float does not change is higher than a fifth threshold, it is determined that the target person's interest in fishing is lower than a second threshold.

8. The method according to any one of claims 1 to 6, characterized in that, The collection of floating image sets within a preset time period, and the environmental information within the preset time period, includes: Based on the first image data, it is determined whether the target person has caught a fish within a preset time. If the target person has not caught a fish within the preset time, a set of floating images within a preset time period, as well as environmental information within the preset time period, are collected.

9. An electronic device, characterized in that, include: The first prediction unit is used to collect first image data of the target person and predict the mental state of the target person based on the first image data. The first acquisition unit is used to acquire a set of floating images within a preset time period, as well as environmental information within the preset time period. The duration of the preset time period exceeds a preset duration. The environmental information includes at least one of the following: weather information and water surface image information. A sampling unit is used to perform feature sampling on each float image in the float image set to obtain a first float image feature sequence; The second prediction unit is used to predict the feeding status of fish in the target area based on the first float image feature sequence and the environmental information, wherein the target area includes the vertical projection area of ​​the float. The reminder unit is used to output a reminder message to the user terminal when the fish feeding state indicates that the probability of fish feeding in the target area is lower than a first preset threshold, and the mental state indicates that the target person's interest in fishing is lower than a second threshold. The reminder message is used to remind the target person that they cannot catch fish in the target area for a short period of time.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the smart terminal reminder method as described in any one of claims 1 to 8.

Images