CN-115620138-B - Intelligent terminal reminding method, electronic equipment and computer readable storage medium

Abstract

The invention discloses an intelligent terminal reminding method, electronic equipment and a computer readable storage medium, wherein the intelligent terminal reminding method comprises the steps of collecting first image data of a target person and predicting the mental state of the target person based on the first image data; the method comprises the steps of collecting a buoy image set in a preset period and environment information in the preset period, carrying out feature sampling on each buoy image in the buoy image set to obtain a first buoy image feature sequence, predicting a fish feeding state of a target area based on the first buoy image feature sequence and the environment information, wherein the target area comprises a vertical projection area of the buoy, and outputting a reminding message to a 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 value and the mental state indicates that the interest of a target person in fishing is lower than a second threshold value. The invention can save the time of the angler.

Inventors

• ZHOU JIEPING

Assignees

• 深圳市启惠智能科技有限公司

Dates

Publication Date

20260508

Application Date

20221024

Claims (10)

1. 1. The intelligent terminal reminding method is characterized by being applied to electronic equipment, wherein the electronic equipment is in communication connection with a user terminal and comprises the following steps: Collecting first image data of a target person, and predicting the mental state of the target person based on the first image data; collecting a buoy image set in a preset time period and environment information in the preset time period, wherein the duration of the preset time period exceeds a preset duration, and the environment information comprises at least one of weather information and water surface image information; Performing feature sampling on each float image in the set of float images to obtain a first float image feature sequence; predicting a fish feeding status of a target area based on the first buoy image feature sequence and the environmental information, the target area comprising a vertically projected area of the buoy; And outputting a reminding 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 value and the mental state indicates that the interest of the target person in fishing is lower than a second threshold value, wherein the reminding message is used for reminding the target person that the target person cannot be fished in the target area in a short time.
2. 2. The method of claim 1, wherein predicting the fish feeding status of the target area based on the first sequence of buoy image features and the environmental information comprises: Performing convolution operation on the float image feature sequence to obtain a float image feature convolution sequence, performing normalization processing on the float image feature convolution sequence to obtain a float image feature normalization sequence, calculating an activation weight coefficient of each feature point in the float image feature normalization sequence, and multiplying each feature point in the float image feature normalization sequence by the activation weight coefficient of the feature point to obtain a second float image feature sequence; predicting a fish feeding status of the target area based on the second sequence of buoy image features and the environmental information.
3. 3. The method of claim 2, wherein the environmental information includes weather information and water surface image information; The predicting a feeding status of the fish in the target area based on the second sequence of float image features and the environmental information, comprising: Acquiring a weather information sample, a water surface image information sample and a float image feature sequence sample and target fish feeding label information, and performing iterative training on an initial network module based on the weather information sample, the water surface image information sample, the float image feature sequence sample and the target fish feeding label information to obtain a target network module for predicting fish feeding state based on the float image feature sequence, the weather information and the water surface image information; And inputting the second buoy image characteristic sequence, the weather information and the water surface image information into the target network module for prediction to obtain the feeding state of the fish in the target area.
4. 4. The method according to claim 2, wherein the method further comprises: Collecting second image data of the target person, wherein the second image data comprises target fish food of the target person hung on a fishhook, and predicting target fish seeds of the target person based on the target fish food; The predicting a feeding status of the fish in the target area based on the second sequence of float image features and the environmental information, comprising: Predicting a fish feeding status of the target fish species in a target area based on the second sequence of buoy image features and the environmental information.
5. 5. The method of claim 4, wherein predicting the fish feeding status of the target fish species in the target region based on the second sequence of buoy image features and the environmental information comprises: Searching eating information of the target fingerlings under the weather information in a preset database, wherein the preset database stores information of a plurality of fingerlings in advance, and the information of each fingerling comprises eating information under a plurality of weather; And predicting the fish eating state of the target fish species in the target area based on the eating information of the target fish species under the weather information, the second buoy image feature sequence and the water surface image information.
6. 6. The method of claim 5, wherein predicting the fish eating status of the target fish species in the target area based on the eating information of the target fish species under the weather information, the second sequence of float image features, and the water surface image information comprises: identifying characteristic information of the water surface image information, wherein the characteristic information is used for representing the state of bubbles on the water surface; Judging whether the number of bubbles generated on the water surface in a preset time is smaller than a third preset threshold value or not based on the bubble state; And when the number of bubbles generated on the water surface in the preset time is smaller than a third preset threshold value, and the feeding information indicates that the feeding desire of the target fish species is lower than the third preset threshold value under the weather information, judging whether the motion of the float is frequently in a gradually reduced state or not based on the second float image feature sequence, and predicting the fish feeding state of the target fish species in the target area if the motion of the float is frequently in the gradually reduced state.
7. 7. The method of any one of claims 1 to 6, wherein the acquiring the first image data of the target person, predicting the mental state of the target person based on the first image data, comprises: Collecting an image dataset of the target person during the prediction period, each image data in the image dataset comprising a hand of the target person, a fishing rod and the float; Identifying a casting rod frequency of the target person based on the image dataset; Identifying motion content of the float at each lifting of the target person, wherein the motion content comprises at least one of unchanged float, moving float, ascending float and descending float; And predicting the mental state of the target person based on the casting rod frequency of the target person and the action content of the float when the rod is lifted each time, wherein when the casting rod frequency is lower than a fourth threshold value and the proportion of the lifting rod which is unchanged by the float in the prediction period is higher than a fifth threshold value, the interest of the target person in fishing is determined to be lower than a second threshold value.
8. 8. The method according to any one of claims 1 to 6, wherein the acquiring a set of buoy images over a preset period of time, and environmental information over the preset period of time, comprises: judging whether the target person is in the middle of the fish in the preset time or not based on the first image data, and if the target person is not in the middle of the fish in the preset time, collecting a buoy image set in a preset time period and environment information in the preset time period.
9. 9. An electronic device, comprising: A first prediction unit configured to acquire first image data of a target person, and predict a mental state of the target person based on the first image data; the first acquisition unit is used for acquiring a buoy image set in a preset period and environment information in the preset period, wherein the duration of the preset period exceeds a preset duration, and the environment information comprises at least one of weather information and water surface image information; The sampling unit is used for carrying out feature sampling on each float image in the float image set to obtain a first float image feature sequence; a second prediction unit for predicting a fish feeding status of a target area based on the first buoy image feature sequence and the environmental information, the target area including a vertical projection area of the buoy; The reminding unit is used for outputting a reminding 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 value and the mental state indicates that the interest of the target person in fishing is lower than a second threshold value, and the reminding message is used for reminding the target person that the fish cannot be fished in the target area in a short time.
10. 10. A computer readable storage medium having stored thereon a computer program, characterized in that the program when executed by a processor realizes the steps in the intelligent terminal reminding method according to any of claims 1 to 8.

Description

Intelligent terminal reminding method, electronic equipment and computer readable storage medium Technical Field The invention belongs to the technical field of electronic equipment, and particularly relates to an intelligent terminal reminding method, electronic equipment and a computer readable storage medium. Background Fishing is more and more popular at present, the number of people in fishing is rapidly increased in recent years, and the network traffic of fishing in the network is heavier and heavier. As the network traffic of fishing increases, more and more people carry various devices, such as various photographing devices, while fishing. However, these devices only shoot the fishing activities, and cannot assist the fisher, so that the fisher cannot judge the fish nature for some new fishing workers, and thus some fishers are easy to waste time. Disclosure of Invention The embodiment of the invention provides an intelligent terminal reminding method, electronic equipment and a computer readable storage medium, which are used for solving the problem that a angler is easy to waste time. The invention provides an intelligent terminal reminding method which is applied to electronic equipment, wherein the electronic equipment is in communication connection with a user terminal and comprises the following steps: Collecting first image data of a target person, and predicting the mental state of the target person based on the first image data; collecting a buoy image set in a preset time period and environment information in the preset time period, wherein the duration of the preset time period exceeds a preset duration, and the environment information comprises at least one of weather information and water surface image information; Performing feature sampling on each float image in the set of float images to obtain a first float image feature sequence; predicting a fish feeding status of a target area based on the first buoy image feature sequence and the environmental information, the target area comprising a vertically projected area of the buoy; And outputting a reminding 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 value and the mental state indicates that the interest of the target person in fishing is lower than a second threshold value, wherein the reminding message is used for reminding the target person that the target person cannot be fished in the target area in a short time. The present invention also provides an electronic device including: A first prediction unit configured to acquire first image data of a target person, and predict a mental state of the target person based on the first image data; the first acquisition unit is used for acquiring a buoy image set in a preset period and environment information in the preset period, wherein the duration of the preset period exceeds a preset duration, and the environment information comprises at least one of weather information and water surface image information; The sampling unit is used for carrying out feature sampling on each float image in the float image set to obtain a first float image feature sequence; a second prediction unit for predicting a fish feeding status of a target area based on the first buoy image feature sequence and the environmental information, the target area including a vertical projection area of the buoy; The reminding unit is used for outputting a reminding 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 value and the mental state indicates that the interest of the target person in fishing is lower than a second threshold value, and the reminding message is used for reminding the target person that the fish cannot be fished in the target area in a short time. The invention also provides a computer readable storage medium having stored thereon a computer program, characterized in that the program when executed by a processor realizes steps in a method for reminding an intelligent terminal. The method comprises the steps of collecting first image data of a target person, predicting the mental state of the target person based on the first image data, collecting a float image set in a preset period and environment information in the preset period, wherein the time of the preset period exceeds the preset time, the environment information comprises at least one item of weather information and water surface image information, feature sampling is conducted 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 environment information, the target area comprises a vertical projection area of the float, and when the feeding state of fish indicates th