Intelligent fishing rod

Abstract

The invention relates to an intelligent fishing rod which comprises a fishing rod body and further comprises a rod swinging judgment module, a rod swinging judgment module and a rod swinging judgment module. The tension detection module is used for detecting the strain force borne by the fishing rod body; the line throwing length detection module is used for detecting the length of a fishing line released by a line wheel of the fishing rod body; the control module is used for receiving data sent by the swing judgment module, the tension detection module and the line throwing length detection module so as to respectively calculate the accumulated swing frequency, the fish weight and the real-time line throwing length in the fishing process, and sending the data to a client through the wireless communication module. According to the intelligent fishing rod, efficiency improvement and experience innovation are brought to fishing activities through the functions of data quantification, social interaction and the like, the core value of the intelligent fishing rod lies in that traditional fishing experience is converted into visual data, the fishing activities and social sharing scenes are innovatively linked in real time, the fishing process is not interrupted, and the fishing efficiency is improved. And fishing experience and social interaction are both considered.

Description

Technical Field

[0001] This invention relates to the field of fishing tackle. More specifically, this invention relates to a smart fishing rod. Background Technology

[0002] Currently, there are many types of smart fishing rods on the market, mainly divided into three categories. The first type achieves automatic fishing through automatic hook setting and reeling, suitable for scenarios requiring long periods of waiting or night fishing. The second type uses intelligent fish-finding devices to help anglers more accurately determine the location of fish. The third type uses lights, sounds, or vibrations to promptly alert the angler. It is evident that existing smart fishing rods primarily focus on increasing the catch rate, neglecting data quantification and social interaction functions. Therefore, it is necessary to develop a smart fishing rod that balances the fishing experience with social interaction. Summary of the Invention

[0003] The purpose of this invention is to provide a smart fishing rod that brings efficiency improvement and experience innovation to fishing activities through data quantification, social interaction and other functions. Its core value lies in transforming traditional fishing experience into visualized data and innovatively linking fishing activities with social sharing scenarios in real time without interrupting the fishing process, thus taking into account both the fishing experience and social interaction.

[0004] To achieve these and other advantages according to the present invention, a smart fishing rod is provided, comprising a rod body and further comprising:

[0005] The swing judgment module is set with acceleration and angular velocity information of the fishing rod body;

[0006] A tensile force detection module is used to detect the strain force on the fishing rod body;

[0007] A line length detection module is used to detect the length of fishing line released from the reel of the fishing rod body;

[0008] The control module receives data from the swing judgment module, the tension detection module, and the casting length detection module. It calculates the cumulative number of swings, the weight of the fish caught, and the real-time casting length during the fishing process. Combining the acceleration and angular velocity information of the fishing rod body, the strain force on the fishing rod body, and the real-time casting length, it calculates the mass index of each swing. The control module then transmits the cumulative number of swings, the weight of the fish caught, the real-time casting length, and the mass index of each casting to the client via a wireless communication module.

[0009] Furthermore, in the aforementioned intelligent fishing rod, the control module calculates the mass index of each swing using the following formula (1):

[0010] (1)

[0011] in, The quality index of each swing; The length of the parabola; To release energy; For input energy; This represents the maximum strain force experienced by the fishing rod body during the swing. The total mass of the fishing rig; The moment when the acceleration of the fishing rod body drops to zero; The moment when the fishing rod body is subjected to the maximum strain force; It is a positive number;

[0012] The calculation method is as follows:

[0013] (2)

[0014] in, At time t, the fishing rod body is subjected to strain force; Let t be the displacement of the rod tip relative to the handle of the fishing rod body at time t;

[0015] The calculation method is as follows:

[0016] (3)

[0017] in, The mass of the fishing rod body; This refers to the maximum speed of the fishing rod body during the swing.

[0018] Furthermore, in the aforementioned smart fishing rod, the method by which the control module determines the swing is as follows:

[0019] Obtain the real-time acceleration and angular velocity of the fishing rod body;

[0020] When the real-time acceleration and angular velocity of the fishing rod body are higher than the preset acceleration threshold and angular velocity threshold respectively, and this continues for multiple sampling points, it is determined that the fishing rod body has entered the acceleration phase, and the current moment is taken as the starting moment.

[0021] After entering the acceleration phase, if the acceleration difference changes from positive to negative, it is determined that the fishing rod body has entered the peak phase.

[0022] After entering the peak stage, when the real-time acceleration and angular velocity of the fishing rod body are lower than the preset acceleration threshold and angular velocity threshold respectively, and after multiple sampling points, it is determined that the fishing rod body has entered the deceleration stage and the current time is taken as the endpoint time.

[0023] If the time taken for the fishing rod body from the start time to the end time is greater than the shortest effective swing time but less than the longest effective swing time, it is determined as a valid swing, and the cumulative number of swings is incremented by one.

[0024] Furthermore, in the aforementioned smart fishing rod, the tension detection module is a micro strain gauge, which is installed at the base of the fishing rod body.

[0025] Furthermore, in the aforementioned smart fishing rod, the control module calculates the weight of the fish caught after receiving the strain force on the fishing rod body sent by the tension detection module, as follows:

[0026] Calculate the weight of the fish catch using the following formula (4):

[0027] (4)

[0028] in, The weight of the fish caught; For the tension of the fishing line; Basic calibration coefficients; This is the rod angle compensation coefficient, which is related to the angle between the rod body and the horizontal plane.

[0029] Furthermore, in the aforementioned intelligent fishing rod, the calculation method for the fishing rod angle compensation coefficient in formula (4) above is as follows:

[0030] The weight is The catch is hung on the hook of the fishing rod body, and the angle between the fishing rod body and the horizontal plane is maintained. ,0< <90°, read the strain force F1 on the fishing rod body measured by the tension detection module;

[0031] The theoretical strain force F0 on the fishing rod body is calculated according to the following formula (2);

[0032] (5)

[0033] at this time That is, the angle between the fishing rod body and the horizontal plane is... The rod angle compensation coefficient at that time;

[0034] By selecting multiple different angles, the rod angle compensation coefficient is calculated for each angle. Then, linear programming is performed to obtain the mapping relationship between the rod angle compensation coefficient and the angle between the rod body and the horizontal plane.

[0035] (6)

[0036] The control module obtains the angle between the fishing rod body and the horizontal plane through the IMU module, and substitutes it into the above formula (3) to obtain the fishing rod angle compensation coefficient. The value of .

[0037] Furthermore, in the aforementioned intelligent fishing rod, the casting length detection module is a reel encoder, which is installed on the reel of the fishing rod body to obtain the number of rotations of the reel.

[0038] Furthermore, the aforementioned smart fishing rod also includes:

[0039] Fishhook acceleration detection module, which is used to obtain the real-time acceleration of the fishhook;

[0040] The float acceleration detection module is used to obtain the real-time acceleration of the float.

[0041] The control module integrates the neural network model. The control module receives the real-time acceleration of the fishhook sent by the fishhook acceleration detection module and the real-time acceleration of the float sent by the float acceleration detection module to obtain the acceleration change information of the fishhook and the float phase change information of the float. The information is then input into the neural network model to obtain the type of fish that has taken the bait, and a lifting plan is sent to the client based on the type of fish.

[0042] Furthermore, in the aforementioned smart fishing rod, the control module has a built-in first database containing various rod-lifting schemes corresponding to different types of fish. After obtaining the type of fish that has taken the bait through a neural network model, the corresponding rod-lifting scheme is selected from the database based on the type of fish and sent to the client.

[0043] Furthermore, the aforementioned smart fishing rod also includes:

[0044] Fishhook acceleration detection module, which is used to obtain the real-time acceleration of the fishhook;

[0045] The float acceleration detection module is used to obtain the real-time acceleration of the float.

[0046] Fishing line tension detection module, which is used to obtain the real-time tension of the fishing line;

[0047] The control module integrates the neural network model. The control module receives the real-time acceleration of the hook sent by the hook acceleration detection module, the real-time acceleration of the float sent by the float acceleration detection module, and the real-time tension of the fishing line generated by the fishing line tension detection module. It then inputs these data into the neural network model to obtain the type and weight of the fish that has taken the bait, and sends a lifting plan to the client based on the type and weight of the fish.

[0048] Furthermore, in the aforementioned smart fishing rod, the control module has a built-in second database, which stores various rod-lifting schemes corresponding to different types and weights of fish. After obtaining the type and weight of the fish that has taken the bait through a neural network model, the corresponding rod-lifting scheme is selected from the second database based on the type and weight of the fish and sent to the client.

[0049] The beneficial effects of this invention are:

[0050] 1. The intelligent fishing rod of the present invention integrates swing counting, fish weight calculation and casting length detection. Through data quantification, social interaction and other functions, it brings efficiency improvement and experience innovation to fishing activities. Its core value lies in transforming traditional fishing experience into visualized data and innovatively linking fishing activities with social sharing scenarios in real time without interrupting the fishing process, taking into account both fishing experience and social interaction.

[0051] 2. This invention is based on information from numerous successful fish catches, including changes in hook acceleration, float movement, and fish species and weight. Using a neural network approach, a neural network model is constructed. During fishing, this model uses real-time information from hook acceleration and float movement to predict the species and weight of the fish that has taken the bait. Based on this information, the model retrieves the corresponding lifting strategy from a database and outputs it. Anglers can then use this strategy to lift the rod, thus increasing the probability of catching a fish.

[0052] Other advantages, objectives and features of the present invention will become apparent in part from the following description, and in part from those skilled in the art through study and practice of the invention. Attached Figure Description

[0053] Figure 1 This is a structural diagram of a fishing rod according to one embodiment of the present invention;

[0054] Figure 2 This is a structural diagram of a fishing rod according to another embodiment of the present invention;

[0055] Figure 3 This is a structural diagram of a fishing rod according to another embodiment of the present invention. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the embodiments of this application, so that those skilled in the art can implement them based on the description. Obviously, the described embodiments are some embodiments of this application, but not all embodiments.

[0057] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0058] First, a brief introduction to the design concept of the embodiments of this application will be given.

[0059] like Figure 1 As shown, an embodiment of the present invention provides a smart fishing rod, including a fishing rod body, and further comprising:

[0060] The swing judgment module is set with acceleration and angular velocity information of the fishing rod body;

[0061] A tensile force detection module is used to detect the strain force on the fishing rod body;

[0062] A line length detection module is used to detect the length of fishing line released from the reel of the fishing rod body;

[0063] The control module receives data from the swing judgment module, the tension detection module, and the casting length detection module. It calculates the cumulative number of swings, the weight of the fish caught, and the real-time casting length during the fishing process. Combining the acceleration and angular velocity information of the fishing rod body, the strain force on the fishing rod body, and the real-time casting length, it calculates the mass index of each swing. The control module then transmits the cumulative number of swings, the weight of the fish caught, the real-time casting length, and the mass index of each casting to the client via a wireless communication module.

[0064] In this embodiment, by integrating multiple modules working collaboratively, the problems of unquantifiable data and lack of social interaction during fishing are solved, achieving precise monitoring and data sharing of fishing behavior. Specifically, the swing judgment module installed in the fishing rod handle can capture the motion characteristics of the swing action in real time, thereby accurately calculating the cumulative number of swings. This is because the handle position, as the pivot of the swing motion, can effectively sense changes in acceleration and angular velocity, avoiding misjudgments caused by external interference and providing a reliable basis for quantifying fishing skills. Based on the strain force of the fishing rod body detected by the tension detection module, the fishing line tension can be derived and the weight of the catch can be calculated. This is because strain force directly reflects the magnitude of external force, and combined with the structural characteristics of the fishing rod, it ensures the accuracy of weight calculation and solves the problem of traditional methods relying on subjective experience. Based on the reel rotation monitored by the casting length detection module, the real-time casting length can be accurately obtained. This is because there is a linear relationship between the number of reel rotations and the length of fishing line release. By directly measuring the reel state, distance estimation deviations caused by environmental factors are avoided, improving the real-time performance and reliability of casting data. The control module calculates key fishing parameters based on the received multi-source data and sends them to the client via wireless communication. This not only enables the automatic quantification of the number of swings, the weight of the catch, and the length of the casting line, but also allows the data to be shared in real time to social platforms via wireless transmission, enabling users to interact and share their fishing results instantly, thus making up for the lack of data application and social functions in existing technologies.

[0065] Preferably, in another embodiment of the present invention, the control module further calculates the mass index of each swing by combining the acceleration and angular velocity information of the fishing rod body, the strain force on the fishing rod body, and the real-time casting length. Specifically:

[0066] Calculate using the following formula (1):

[0067] (1)

[0068] in, The quality index of each swing; The length of the parabola; To release energy; For input energy; This represents the maximum strain force experienced by the fishing rod body during the swing. The total mass of the fishing rig; The moment when the acceleration of the fishing rod body drops to zero; The moment when the fishing rod body is subjected to the maximum strain force; It is a positive number;

[0069] In the above formula (1), The core efficiency ratio (CER) is ideally close to 1, meaning that almost all the energy input by the angler is wasted (e.g., energy lost as muscle fatigue, unnecessary rod vibration, air friction, etc.), and is effectively stored by the rod and released to the fishing rig. An actual CER value < 1 indicates losses exist. The higher the ratio, the more efficient the energy transfer path. A poorly executed cast, even with significant brute force, will still result in losses. However, a significant amount of energy is lost during the transfer process. If it's very low, the core efficiency ratio will be very small.

[0070] In the above formula (1), The specific load factor is used to diagnose equipment matching and load levels. A specific load factor that is too high means the rod is excessively bent, possibly due to using too heavy a lure or applying too much force. This can lead to stiff casting, a high risk of line breakage, and even rod damage. A specific load factor that is too low means the rod is not fully loaded, possibly due to a too-light lure or insufficient force, preventing the rod's elastic energy from being fully utilized. There is a "golden range" for the specific load factor: for a specific rod action and stiffness, there exists an optimal range when paired with a specific weight of lure. Within this range, the elasticity of the fishing rod body is optimally utilized.

[0071] In the above formula (1), It is used to quantify the coordination between the angler's swing timing and the dynamic response of the fishing rod itself. This is the moment when the strain force on the fishing rod reaches its peak. This marks the instant when the rod's bending angle reaches its maximum and the stored elastic potential energy reaches its peak. After this moment, the fishing rod begins to rebound rapidly, releasing energy. The moment the acceleration of the fishing rod reaches zero marks the end of the angler's active force application. After this point, the fishing rod moves due to inertia. and They should be achieved simultaneously, but this is clearly difficult to achieve, therefore... This indicates a timing misalignment, under ideal conditions. infinitely close Just as the angler stops exerting force, the fishing rod is bent to its limit, indicating that the angler's force is completely "caught" and converted by the fishing rod, and no force "hit empty space" or causes unstable vibration of the rod. Earlier This means that if the angler continues to accelerate after the fishing rod is fully bent, the force will "push" against the already rebounding fishing rod, causing energy collision and vibration. Later This means that the angler has stopped applying force, but the fishing rod is still bending (commonly known as "waiting for the rod to bend"). This indicates that the initial acceleration was insufficient or the force was not applied decisively, resulting in a delay in loading and a sluggish release of energy. It is a very small normal number (e.g., 0.01 seconds) to prevent when hour The denominator is zero.

[0072] The calculation method is as follows:

[0073] (2)

[0074] in, At time t, the fishing rod body is subjected to strain force; Let t be the displacement of the rod tip relative to the handle of the fishing rod body at time t;

[0075] The fishing rod itself has good elasticity; it can spring back like a spring after bending (storing energy). The net positive work done on the fishing rig (i.e., the bait and leader line) is directly converted into the kinetic energy of the rig's flight. In calculations... At the same time, by combining the rod body strain and rod tip trajectory data, strain gauges can be used to obtain the real-time strain force of the fishing rod body. An IMU is installed at the rod tip to obtain the displacement of the rod tip relative to the handle. In equation (2) above, the integral interval covers the entire process from the start of loading to the end of release. This approximates the portion of the area enclosed by the fishing rod load-deformation curve (similar to the stress-strain curve) that represents the energy release.

[0076] The calculation method is as follows:

[0077] (3)

[0078] in, The mass of the fishing rod body; This refers to the maximum speed of the fishing rod body during the swing.

[0079] The total work done by the angler on the fishing rod through their hands and body during the swing is approximately equal to the peak kinetic energy of the fishing rod during the swing.

[0080] In this embodiment, the final result of the swing is that the angler, through precise acceleration, stimulates the fishing rod to generate an ideal load-rebound curve, thereby maximizing the conversion of energy into the casting length. To quantify the quality of the swing, this embodiment proposes a swing quality index. First, it's about matching the angler's swing motion with the rod itself, ensuring the swing perfectly matches the rod's action and power. Second, it's about energy transfer efficiency: minimizing energy loss at each step from the swing's kinetic energy to the rod's potential energy and then to the rig's kinetic energy. Specifically, swing speed, as an input-driven indicator, depends on the angler's initial movement speed; swing acceleration, as an input quality indicator, determines the smoothness and efficiency of energy input, affecting the timing and pattern of the rod's initial loading (bending); and the real-time strain force on the rod, as a process indicator, directly reflects: 1. Energy storage: the accumulation of bending potential energy in the rod during the strain force rise phase; 2. Energy release: the process of the rod rebounding and converting potential energy into rig kinetic energy after the strain force peak; 3. Action coordination: ideally, the strain force curve should have an appropriate phase difference with the swing acceleration curve, forming a perfect "loading-release" rhythm.

[0081] In summary, It is actually the product of distance, energy efficiency, and timing accuracy:

[0082] For "brute force" type throws, It might be good, but... Low( Small), It was also low (due to a large misalignment in timing), ultimately leading to The value is not high;

[0083] For "unskilled" throwers, It might be good, but Inappropriate (mismatched bait and rod), resulting in Very short, ultimately leading to The value is not high;

[0084] For a "master-level" throw, Reaching or approaching the theoretical limit, Extremely high, with an energy conversion ratio close to 1 and a specific load in the golden range. Extremely high, with the moment of force application stopping and the moment the rod is fully drawn almost perfectly synchronized. Multiplying these three factors together yields an extremely high CPQI value.

[0085] Preferably, as another embodiment of the present invention, the method by which the control module determines the swing is as follows:

[0086] Obtain the real-time acceleration and angular velocity of the fishing rod body;

[0087] When the real-time acceleration and angular velocity of the fishing rod body are higher than the preset acceleration threshold and angular velocity threshold respectively, and this continues for multiple sampling points, it is determined that the fishing rod body has entered the acceleration phase, and the current moment is taken as the starting moment.

[0088] After entering the acceleration phase, if the acceleration difference changes from positive to negative, it is determined that the fishing rod body has entered the peak phase.

[0089] After entering the peak stage, when the real-time acceleration and angular velocity of the fishing rod body are lower than the preset acceleration threshold and angular velocity threshold respectively, and after multiple sampling points, it is determined that the fishing rod body has entered the deceleration stage and the current time is taken as the endpoint time.

[0090] If the time taken for the fishing rod body from the start time to the end time is greater than the shortest effective swing time but less than the longest effective swing time, it is determined as a valid swing, and the cumulative number of swings is incremented by one.

[0091] In this embodiment, the swing detection module is an IMU module. The control module receives acceleration and angular velocity information sent by the IMU module. By introducing the IMU module and designing a phased dynamic judgment logic, the problem of misjudgment in swing detection is effectively solved. The core lies in using dual thresholds of acceleration and angular velocity to determine the acceleration phase, avoiding false triggering caused by environmental interference due to relying on only a single parameter. For example, wind or slight shaking cannot simultaneously meet the dual threshold conditions, thus accurately capturing the swing start point. After the acceleration phase, the peak phase is identified based on the turning feature of the acceleration difference from positive to negative. This design is based on the physical characteristics of the swing action—the change in the sign of the difference corresponds to the instantaneous state when the swing force reaches its peak, ensuring the objectivity of the peak judgment rather than simply relying on a fixed time point, effectively distinguishing between a real swing and non-periodic jitter. Subsequently, after the peak phase, the deceleration phase begins as the acceleration and angular velocity fall below the threshold. The swing end is verified by dual parameters, preventing external disturbances during deceleration from being misjudged as new movements. Finally, by combining the duration constraint from the acceleration to the deceleration phase and filtering valid movements based on a preset swing time threshold, this mechanism utilizes the rapid temporal characteristics of a real swing to exclude time-consuming operations such as slow posture adjustments, ensuring that only movements conforming to the inherent temporal characteristics of the swing are counted. Overall, this phased judgment method significantly improves the robustness of swing recognition by dynamically capturing the physical characteristics of the entire swing process, providing a reliable foundation for the accurate statistics of cumulative swing counts.

[0092] Preferably, as another embodiment of the present invention, the tensile force detection module is a micro strain gauge, which is installed at the base of the fishing rod body.

[0093] In this embodiment, by defining the tension detection module as a micro-strain gauge and installing it at the base of the fishing rod, the problem of inaccurate strain measurement is effectively solved. As the core component of the tension detection module, the micro-strain gauge can highly sensitively capture the minute deformations of the fishing rod under stress. This is because the strain gauge, based on the principle of resistance change, has a linear response characteristic to local strain, thus providing an accurate raw data foundation for subsequent calculations. The installation location is chosen at the base of the fishing rod because the base bears the maximum strain during the rod's bending process and is far from moving parts such as the reel, avoiding interference signals from casting or environmental vibrations, ensuring that the detected strain directly corresponds to the fishing line tension. This design allows the control module to more accurately reflect the force exerted by the fish on the fishing rod when receiving strain data, providing a stable and reliable input for calculating the fish weight and avoiding system errors caused by improper measurement point selection.

[0094] Preferably, as another embodiment of the present invention, the control module calculates the weight of the fish catch after receiving the strain force on the fishing rod body sent by the tension detection module as follows:

[0095] Calculate the weight of the fish catch using the following formula (4):

[0096] (4)

[0097] in, The weight of the fish caught; For the tension of the fishing line; Basic calibration coefficients; This is the rod angle compensation coefficient, which is related to the angle between the rod body and the horizontal plane.

[0098] The calculation method for the rod angle compensation coefficient in formula (4) above is as follows:

[0099] The weight is The catch is hung on the hook of the fishing rod body, and the angle between the fishing rod body and the horizontal plane is maintained. ,0< <90°, read the strain force F1 on the fishing rod body measured by the tension detection module;

[0100] The theoretical strain force F0 on the fishing rod body is calculated according to the following formula (2);

[0101] (5)

[0102] at this time That is, the angle between the fishing rod body and the horizontal plane is... The rod angle compensation coefficient at that time;

[0103] By selecting multiple different angles, the rod angle compensation coefficient is calculated for each angle. Then, linear programming is performed to obtain the mapping relationship between the rod angle compensation coefficient and the angle between the rod body and the horizontal plane.

[0104] (6)

[0105] The control module obtains the angle between the fishing rod body and the horizontal plane through the IMU module, and substitutes it into the above formula (3) to obtain the fishing rod angle compensation coefficient. The value of .

[0106] In this embodiment, by constructing a calculation model that includes an angle compensation coefficient, the impact of rod posture changes on the accuracy of fish catch weight quantification is effectively solved, ensuring the reliability of data under different fishing scenarios. The control module receives strain data sent by the tension detection module as the basic input, which directly reflects the fishing line tension F, providing the original basis for weight calculation. The calculation is performed using the formula M=F∙α∙β, where F is the real-time measured fishing line tension, and its value comes from the strain gauge output of the tension detection module, avoiding the accumulation of errors caused by relying solely on fixed calibration values; α is the basic calibration coefficient, which is used to compensate for system deviations introduced by the inherent characteristics of the sensor and the installation position, such as the correction of the measurement benchmark in the horizontal rod holding state, ensuring the accuracy of the initial calculation environment; β is the rod angle compensation coefficient, whose value is dynamically related to the angle between the rod body and the horizontal plane. The key is to adjust the weight of the tension component according to the actual angle. For example, when the rod angle increases, the vertical component of gravity decreases, resulting in a lower strain measurement value. β automatically amplifies the correction ratio through the mapping relationship, thereby offsetting the interference of angle changes on tension measurement. This method of dynamically generating compensation coefficients based on the real-time angle of the fishing rod not only preserves the original data value of strain testing, but also achieves adaptive correction for non-standard rod-holding postures by introducing angle information, making the calculated fish weight M closer to the true value and avoiding the systematic errors caused by ignoring angle factors in traditional methods.

[0107] Preferably, as another embodiment of the present invention, the casting length detection module is a reel encoder, which is installed on the reel of the fishing rod body to obtain the number of rotations of the reel.

[0108] like Figure 2 As shown, preferably, as another embodiment of the present invention, the intelligent fishing rod further includes:

[0109] Fishhook acceleration detection module, which is used to obtain the real-time acceleration of the fishhook;

[0110] The float acceleration detection module is used to obtain the real-time acceleration of the float.

[0111] The control module integrates the neural network model. The control module receives the real-time acceleration of the fishhook sent by the fishhook acceleration detection module and the real-time acceleration of the float sent by the float acceleration detection module to obtain the acceleration change information of the fishhook and the float phase change information of the float. The information is then input into the neural network model to obtain the type of fish that has taken the bait, and a lifting plan is sent to the client based on the type of fish.

[0112] This embodiment primarily addresses the challenge for novice anglers who struggle to accurately determine the type of fish biting the hook based on float movements, thus hindering their ability to seize the optimal time to set the hook. Specifically, a large amount of data is collected beforehand, capturing information on hook acceleration changes, float movement changes, and fish species information each time a fish is hooked. This data serves as the training set to train a constructed neural network, resulting in a neural network model that establishes the relationship between hook acceleration changes, float movement changes, and fish species information. Specifically, an accelerometer can be placed near the hook on the fishing line to detect the hook's real-time acceleration, retaining recent acceleration changes as the hook's acceleration information. Similarly, an accelerometer can be placed inside the float or near the float on the fishing line to detect the float's real-time acceleration, retaining recent acceleration changes as the float's movement information.

[0113] Later, during fishing, by acquiring real-time information on changes in hook acceleration and float movement, a neural network model can determine the type of fish biting the hook. Based on the fish type, it can output a lifting strategy, achieving automatic identification of the biting fish and providing lifting guidance. This effectively overcomes the shortcomings of beginners' subjective judgment of float movements, ensuring the objectivity and timeliness of lifting decisions. To address the problem of beginners struggling to identify fish species by accurately judging float movements, multiple fish-biting data points were collected and a training set was built. This data included at least information on hook acceleration changes, float movement changes, and fish species. This feature was developed by collecting multi-dimensional data from real fishing scenarios, specifically building a training set based on the correlation between hook acceleration changes, float movement changes, and fish species. This allows the system to learn the dynamic characteristic patterns of different fish biting the hook, avoiding the subjectivity and inaccuracy of relying solely on a single float movement observation, and providing a reliable data foundation for model training. A neural network was established, using information on changes in hook acceleration and float movement from the training set as input layers, and fish species as the training set. This input was used to train the neural network model, resulting in a model that fully utilizes the objectivity and richness of sensor data. The model automatically extracts key features of the biting behavior and establishes a mapping relationship with fish species. This multi-source data-based training method significantly improves the robustness of recognition and solves the problem of beginners' insufficient understanding of float movement changes. When fishing with a smart fishing rod, information on changes in hook acceleration and float movement is acquired and input into the neural network model to determine the species of fish biting. In actual fishing, this feature, based on real-time hook acceleration and float movement data, enables instant identification of the biting fish species. In particular, by replacing subjective float movement judgments with objective sensor data, timely decision-making is ensured and human error is reduced, allowing beginners to obtain accurate fish species information. Based on the type of fish, this feature outputs a corresponding lifting action. It is specially customized according to the type of fish, and provides operation guidance directly for the characteristics of different fish. This ensures the accuracy of the timing of the lifting action and the effectiveness of the action, thereby helping beginners avoid problems such as getting the hook off or breaking the line due to misjudging the type of fish.

[0114] Preferably, in another embodiment of the present invention, the control module has a built-in first database, which stores a variety of lifting schemes corresponding to different types of fish. After obtaining the type of fish that has taken the bait through a neural network model, the corresponding lifting scheme is selected from the database according to the type of fish and sent to the client.

[0115] In this embodiment, a first database is pre-built. Based on the experience of experienced anglers, a corresponding lifting scheme is constructed for each type of fish. After obtaining the type of fish that has taken the bait through a neural network model, the corresponding lifting scheme is selected from the first database and output to the angler to provide guidance, so that the angler can successfully reel in the fish.

[0116] like Figure 3 As shown, preferably, as another embodiment of the present invention, the intelligent fishing rod further includes:

[0117] Fishhook acceleration detection module, which is used to obtain the real-time acceleration of the fishhook;

[0118] The float acceleration detection module is used to obtain the real-time acceleration of the float.

[0119] Fishing line tension detection module, which is used to obtain the real-time tension of the fishing line;

[0120] The control module integrates the neural network model. The control module receives the real-time acceleration of the hook sent by the hook acceleration detection module, the real-time acceleration of the float sent by the float acceleration detection module, and the real-time tension of the fishing line generated by the fishing line tension detection module. It then inputs these data into the neural network model to obtain the type and weight of the fish that has taken the bait, and sends a lifting plan to the client based on the type and weight of the fish.

[0121] In this embodiment, relying solely on acceleration and float information fails to obtain fish weight data, resulting in a lack of adaptability to fish size in the lifting strategy. It cannot dynamically adjust the lifting force and timing for fish of different weights, easily leading to operational errors such as small fish getting off the hook or large fish breaking the line. This embodiment significantly improves the accuracy of fish feature recognition by integrating fishing line tension change information with fish weight data, thus providing a more comprehensive basis for lifting decisions. When measuring fishing line tension, a tension sensor is installed on the fishing line between the hook and the float to collect the line tension. Specifically, adding fishing line tension change information and fish weight to the fish-hit information overcomes the limitations of relying solely on acceleration and float information. This is because fishing line tension changes directly reflect the fish's pulling strength, and pulling strength is strongly correlated with fish weight. This allows the training data to cover the fish size dimension, avoiding lifting strategy biases caused by relying solely on species judgment. When building the neural network, changes in hook acceleration, float movement, and line tension are used as input layers. This fusion of multi-source information enables the model to capture the complete dynamic characteristics of a fish's bite behavior. The introduction of line tension variation information is particularly crucial, as it supplements the mechanical properties that acceleration and float movement cannot directly represent. This allows the neural network to effectively learn the mapping between tension and fish weight during training, thus using fish species and weight as joint output targets, rather than just species. In actual fishing, real-time acquisition of acceleration, float movement, and tension variation information is input into the model. The model output includes both species and weight, allowing for customized rod-lifting strategies based on specific sizes. For example, a gentle lift can be used for small fish to reduce the risk of them getting off the hook, while a gradual lift can be used for large fish to avoid line breakage, fundamentally optimizing the adaptability and reliability of the rod-lifting action.

[0122] Preferably, in another embodiment of the present invention, the control module has a built-in second database, which stores a variety of lifting schemes corresponding to different types and weights of fish. After obtaining the type and weight of the fish that has taken the bait through a neural network model, the corresponding lifting scheme is selected from the second database according to the type and weight of the fish and sent to the client.

[0123] In this embodiment, for the same type of fish, the required rod lifting force and speed differ depending on the weight, such as the carp at 500 grams versus 2000 grams. This avoids the problem of excessive force leading to hook loss or insufficient force causing the fish to escape, which can occur when choosing a method solely based on fish species. Therefore, each rod lifting method in the second database corresponds to the same type of fish within a certain weight range. After obtaining the type and size of the biting fish through a neural network model, this condition ensures that the method selection strictly relies on real-time and accurate fish information. The complete data output by the neural network provides an objective basis for decision-making, reducing reliance on the angler's experience, and especially solving the pain point of beginners struggling to judge fish size based on float movements. The corresponding rod lifting method is selected from the second database based on the type and size of the fish and output. This dynamic matching mechanism based on two parameters fully utilizes the precise information provided by the neural network, enabling the rod lifting method to adapt to different fish conditions. For example, a gentle rod lifting command is output for small fish to avoid startling them, while a strong rod lifting command is output for large fish to prevent line breakage. Ultimately, this helps users seize the best time to lift the rod in complex fishing scenarios.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to the embodiments, those skilled in the art should understand that modifications or equivalent substitutions to the technical solutions of this application do not depart from the spirit and scope of the technical solutions of this application, and should all be covered within the scope of the claims of this application.

Claims

1. A smart fishing rod, comprising a rod body, characterized in that, Also includes: The swing judgment module is set with acceleration and angular velocity information of the fishing rod body; A tensile force detection module is used to detect the strain force on the fishing rod body; A line length detection module is used to detect the length of fishing line released from the reel of the fishing rod body; The control module receives data from the swing judgment module, the tension detection module, and the casting length detection module. It calculates the cumulative number of swings, the weight of the fish caught, and the real-time casting length during the fishing process. Combining the acceleration and angular velocity information of the fishing rod body, the strain force on the fishing rod body, and the real-time casting length, it calculates the mass index of each swing. The control module then transmits the cumulative number of swings, the weight of the fish caught, the real-time casting length, and the mass index of each casting to the client via a wireless communication module.

2. The intelligent fishing rod as described in claim 1, characterized in that, The control module calculates the mass index for each swing using the following formula (1): （1） in, The quality index of each swing; The length of the parabola; To release energy; For input energy; This represents the maximum strain force experienced by the fishing rod body during the swing. The total mass of the fishing rig; The moment when the acceleration of the fishing rod body drops to zero; The moment when the fishing rod body is subjected to the maximum strain force; It is a positive number; The calculation method is as follows: （2） in, At time t, the fishing rod body is subjected to strain force; Let t be the displacement of the rod tip relative to the handle of the fishing rod body at time t; The calculation method is as follows: （3） in, The mass of the fishing rod body; This refers to the maximum speed of the fishing rod body during the swing.

3. The intelligent fishing rod as described in claim 1, characterized in that, The swing determination module is an IMU module. The control module receives acceleration and angular velocity information sent by the IMU module. The control module determines the swing as follows: Obtain the real-time acceleration and angular velocity of the fishing rod body; When the real-time acceleration and angular velocity of the fishing rod body are higher than the preset acceleration threshold and angular velocity threshold respectively, and this continues for multiple sampling points, it is determined that the fishing rod body has entered the acceleration phase, and the current moment is taken as the starting moment. After entering the acceleration phase, if the acceleration difference changes from positive to negative, it is determined that the fishing rod body has entered the peak phase. After entering the peak stage, when the real-time acceleration and angular velocity of the fishing rod body are lower than the preset acceleration threshold and angular velocity threshold respectively, and after multiple sampling points, it is determined that the fishing rod body has entered the deceleration stage and the current time is taken as the endpoint time. If the time taken for the fishing rod body from the start time to the end time is greater than the shortest effective swing time but less than the longest effective swing time, it is determined as a valid swing, and the cumulative number of swings is incremented by one.

4. The intelligent fishing rod as described in claim 3, characterized in that, The control module calculates the weight of the catch by receiving the strain force on the fishing rod body sent by the tension detection module as follows: Calculate the weight of the fish catch using the following formula (4): （4） in, The weight of the fish caught; For the tension of the fishing line; Basic calibration coefficients; This is the rod angle compensation coefficient, which is related to the angle between the rod body and the horizontal plane.

5. The intelligent fishing rod as described in claim 4, characterized in that, The calculation method for the rod angle compensation coefficient in formula (4) above is as follows: The weight is The catch is hung on the hook of the fishing rod body, and the angle between the fishing rod body and the horizontal plane is maintained. ,0< <90°, read the strain force F1 on the fishing rod body measured by the tension detection module; The theoretical strain force F0 on the fishing rod body is calculated according to the following formula (2); （5） at this time That is, the angle between the fishing rod body and the horizontal plane is... The rod angle compensation coefficient at that time; By selecting multiple different angles, the rod angle compensation coefficient is calculated for each angle. Then, linear programming is performed to obtain the mapping relationship between the rod angle compensation coefficient and the angle between the rod body and the horizontal plane. （6） The control module obtains the angle between the fishing rod body and the horizontal plane through the IMU module, and substitutes it into the above formula (3) to obtain the fishing rod angle compensation coefficient. The value of .

6. The intelligent fishing rod as described in claim 1, characterized in that, The casting length detection module is a reel encoder, which is installed on the reel of the fishing rod body to obtain the number of rotations of the reel.

7. A smart fishing rod as described in any one of claims 1-6, characterized in that, Also includes: Fishhook acceleration detection module, which is used to obtain the real-time acceleration of the fishhook; The float acceleration detection module is used to obtain the real-time acceleration of the float. The control module integrates the neural network model. The control module receives the real-time acceleration of the fishhook sent by the fishhook acceleration detection module and the real-time acceleration of the float sent by the float acceleration detection module to obtain the acceleration change information of the fishhook and the float phase change information of the float. The information is then input into the neural network model to obtain the type of fish that has taken the bait, and a lifting plan is sent to the client based on the type of fish.

8. The intelligent fishing rod as described in claim 7, characterized in that, The control module has a built-in first database containing various lifting schemes corresponding to different types of fish. After obtaining the type of fish that has taken the bait through a neural network model, the module selects the corresponding lifting scheme from the database based on the type of fish and sends it to the client.

9. A smart fishing rod as described in any one of claims 1-6, characterized in that, Also includes: Fishhook acceleration detection module, which is used to obtain the real-time acceleration of the fishhook; The float acceleration detection module is used to obtain the real-time acceleration of the float. Fishing line tension detection module, which is used to obtain the real-time tension of the fishing line; The control module integrates the neural network model. The control module receives the real-time acceleration of the hook sent by the hook acceleration detection module, the real-time acceleration of the float sent by the float acceleration detection module, and the real-time tension of the fishing line generated by the fishing line tension detection module. It then inputs these data into the neural network model to obtain the type and weight of the fish that has taken the bait, and sends a lifting plan to the client based on the type and weight of the fish.

10. A smart fishing rod as described in claim 9, characterized in that, The control module has a built-in second database that stores various lifting schemes for different types and weights of fish. After obtaining the type and weight of the fish that has taken the bait through a neural network model, the module selects the corresponding lifting scheme from the second database based on the type and weight of the fish and sends it to the client.

Images