Overload detection method and device of shared vehicle, computer equipment, readable storage medium and program product

Abstract

The invention relates to an overload detection method and device of a shared vehicle, computer equipment, a readable storage medium and a program product. The method comprises the following steps: when a user uses a shared vehicle, acquiring the real-time load weight of the shared vehicle; acquiring a first overload threshold value, and judging whether the shared vehicle is overloaded or not by comparing the real-time load weight with the first overload threshold value; wherein the first overload threshold value is an overload threshold value determined based on a user weight model of the user, the user weight model is a normal distribution model pre-constructed based on historical weight records of the user, and the historical weight records are weight records measured through the shared vehicle when the user uses the shared vehicle in the past. By adopting the method, the overload detection accuracy of the shared vehicle can be improved.

Description

Technical Field

[0001] The present application relates to the technical fields of big data and the Internet of Things, and in particular to an overload detection method for a shared vehicle, a computer device, a readable storage medium, and a program product. Background Art

[0002] With the acceleration of urbanization and the increasing awareness of environmental protection, shared transportation models have ushered in rapid development around the world. Among them, shared electric vehicles are gradually being widely used as an effective solution to ease urban traffic pressure and reduce carbon emissions. Many cities have successively promoted the deployment of shared electric vehicles in order to improve the convenience and environmental protection of public transportation. However, with the surge in the number of deployments, some citizens frequently violate regulations when using shared electric vehicles, especially overloading, which is a major safety hazard in the driving of shared electric vehicles, but it has been repeatedly banned. In view of the limitations of traditional offline inspections and fixed-point supervision methods, a more efficient management method is urgently needed. Therefore, with the help of Internet of Things technology, equipping shared electric vehicles with load sensors and effectively supervising overloading behavior through real-time monitoring data have become the key measures to solve this problem.

[0003] At present, in order to solve this problem, many shared electric vehicle manufacturers have installed load sensors under the vehicle seats. The sensors obtain the weight data of the riding users in real time, and use this data to monitor and judge overloading behavior. Specifically, by setting a maximum load limit, when the real-time weight data exceeds the maximum limit, it is judged as overloading. This method may misjudge users who are heavier or carry heavier items.

[0004] Therefore, the accuracy of overload detection of shared transportation vehicles in traditional technologies is not high. Summary of the invention

[0005] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for overloading detection of shared vehicles, which can improve the accuracy of overloading detection of shared vehicles, in order to address the above technical problems.

[0006] In a first aspect, the present application provides a method for detecting overload of a shared vehicle, comprising:

[0007] When a user uses a shared transportation tool, obtaining the real-time load weight of the shared transportation tool;

[0008] Obtaining a first overload threshold, and determining whether the shared transportation vehicle is overloaded by comparing the real-time load weight with the first overload threshold;

[0009] Among them, the first overload threshold is an overload threshold determined based on the user weight model of the user, and the user weight model is a normal distribution model pre-constructed based on the user's historical weight record, and the historical weight record is a weight record measured by the shared transportation vehicle when the user used the shared transportation vehicle in the past.

[0010] In one embodiment, the method further comprises:

[0011] Creating a weight database of the user; the weight database is used to record the multiple data records of the real-time load weight transmitted back by the shared transportation vehicle as multiple weight records of the user;

[0012] When the number of weight records in the weight database is equal to a preset number threshold, a user weight model of the user is constructed according to the weight records stored in the weight database.

[0013] In one embodiment, constructing a user weight model of the user according to the weight records stored in the weight database includes:

[0014] Determining the weight mean and weight standard deviation of the user according to the weight records stored in the weight database;

[0015] The weight mean and the weight standard deviation are used as parameters of the user weight model to construct the user weight model.

[0016] In one embodiment, when the number of weight records in the weight database is greater than the preset number threshold, the method further includes:

[0017] Whenever a new weight record is received, the parameters of the user weight model are updated according to the new weight record;

[0018] In the process of updating the parameters of the user weight model, the influence weight of the new weight record on the parameters of the user weight model is determined according to the time interval between the new weight record and the previous weight record, and the number of weight records in the weight database.

[0019] In one embodiment, the parameters of the user weight model include the user's weight mean and weight standard deviation, and updating the parameters of the user weight model according to the new weight record includes:

[0020] According to a preset first mapping relationship, a frailty factor is determined according to the number of weight records in the weight database; wherein the number of weight records in the weight database is negatively correlated with the value of the frailty factor;

[0021] According to a preset second mapping relationship, the weight coefficient is determined according to the attenuation factor and the time interval; the product of the attenuation factor and the time interval is positively correlated with the weight coefficient;

[0022] According to the weight coefficient and the new weight record, the user's weight mean and weight standard deviation are adjusted to obtain new weight mean and weight standard deviation, so as to update the parameters of the user's weight model.

[0023] In one embodiment, the method further comprises:

[0024] When the number of weight records stored in the weight database is less than the preset number threshold, obtaining a second overload threshold; the second overload threshold is an overload threshold pre-configured by the supervision object of the shared transportation vehicle;

[0025] By comparing the real-time load weight with the second overload threshold, it is determined whether the shared transportation vehicle is overloaded.

[0026] In one embodiment, the parameters of the user weight model include the user's weight mean and weight standard deviation, and obtaining the first overload threshold includes:

[0027] Determine the calculation method of the upper limit of the preset confidence interval through the standard normal distribution table;

[0028] The weight mean and the weight standard deviation are processed according to the upper limit calculation method to obtain an upper limit value of a confidence interval as the first overload threshold.

[0029] In a second aspect, the present application also provides an overload detection device for a shared vehicle, comprising:

[0030] An acquisition module, used to acquire the real-time load weight of a shared transportation vehicle when a user uses the shared transportation vehicle;

[0031] A judgment module, configured to obtain a first overload threshold value, and judge whether the shared transportation vehicle is overloaded by comparing the real-time load weight with the first overload threshold value;

[0032] Among them, the first overload threshold is an overload threshold determined based on the user weight model of the user, and the user weight model is a normal distribution model pre-constructed based on the user's historical weight record, and the historical weight record is a weight record measured by the shared transportation vehicle when the user used the shared transportation vehicle in the past.

[0033] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0034] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0035] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0036] The above-mentioned shared transportation vehicle overload detection method, device, computer equipment, computer-readable storage medium and computer program product obtain the real-time load weight of the shared transportation vehicle during the user's use of the shared transportation vehicle, and judge whether the shared transportation vehicle is overloaded by comparing the real-time load weight with a first overload threshold, wherein the first overload threshold is an overload threshold determined based on the user's user weight model, and the user weight model is a normal distribution model pre-constructed based on the user's historical weight record, and the historical weight record is a record of the weight measured by the shared transportation vehicle when the user used the shared transportation vehicle in the past; in this way, the user's weight characteristics can be effectively and accurately characterized by the user's weight model, and in the process of the user using the shared transportation vehicle, whether the real-time load weight representing the user's weight is significantly deviated from the established user weight model can be detected in real time to judge whether the shared transportation vehicle is overloaded, thereby effectively determining the user's overload behavior and avoiding the risk of misjudgment due to personal weight fluctuations or occasional weight bearing. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0038] FIG1 is a diagram showing an application environment of an overload detection method for a shared vehicle in one embodiment;

[0039] FIG2 is a schematic flow chart of a method for detecting overload of a shared vehicle in one embodiment;

[0040] FIG3 is a schematic flow chart of an overload detection method for a shared vehicle in another embodiment;

[0041] FIG4 is a structural block diagram of an overload detection device for a shared vehicle in one embodiment;

[0042] FIG. 5 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0044] The data collection and processing in this application should be strictly in accordance with the requirements of relevant national laws when applied in practice, and the informed consent or separate consent of the personal information subject should be obtained. Subsequent data use and processing should be carried out within the scope of authorization of laws and regulations and the personal information subject.

[0045] In this application, the implementation of the data capture technical solution involved, when the above embodiments of this application are applied to specific products or technologies, the relevant data collection, use and processing processes should comply with the requirements of national laws and regulations, conform to the principles of legality, legitimacy and necessity, do not involve the acquisition of data types prohibited or restricted by laws and regulations, and will not hinder the normal operation of the target website.

[0046] The overload detection method of the shared vehicle provided in the embodiment of the present application can be applied to the application environment shown in Figure 1. Among them, the shared vehicle 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. In actual applications, when the user uses the shared vehicle 102, the shared vehicle 102 sends the real-time load weight to the server 104, and the server 104 obtains the real-time load weight of the shared vehicle; the server 104 obtains the first overload threshold, and the server 104 determines whether the shared vehicle is overloaded by comparing the real-time load weight with the first overload threshold; wherein the first overload threshold is an overload threshold determined based on the user's user weight model, and the user weight model is a normal distribution model pre-constructed based on the user's historical weight record, and the historical weight record is a weight record measured by the user through the shared vehicle when the user used the shared vehicle in the past. Among them, the shared vehicle 102 can be, but is not limited to, various shared electric vehicles, shared electric skateboards, shared bicycles, shared cars and other vehicles based on shared transportation technology. The server 104 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0047] In an exemplary embodiment, as shown in FIG2 , a method for detecting overload of a shared vehicle is provided, and the method is described by taking the application of the method to the server 104 in FIG1 as an example, and includes the following steps S202 to S204 . Among them:

[0048] Step S202, when the user uses the shared transportation tool, obtain the real-time load weight of the shared transportation tool.

[0049] The shared transportation means may refer to shared electric vehicles, shared electric skateboards, shared bicycles and other vehicles based on shared transportation technology. Taking the shared electric vehicle as an example, a load sensor installed on the shared electric vehicle can be used to collect the current weight of the load object of the shared transportation vehicle (i.e., the real-time load weight) in real time.

[0050] In actual applications, when users ride shared electric vehicles, the real-time load weight collected by the load sensor can be used as the weight of the rider (user) of the shared electric vehicle, and the data collected by the load sensor can be packaged into a data packet through the on-board intelligent central control of the shared electric vehicle; then, the data packet carrying the real-time load weight can be uploaded to the server using a wireless network in a fixed standard interface format; the server parses the data packet to obtain the real-time load weight transmitted back by the shared vehicle.

[0051] Step S204, obtaining a first overload threshold, and determining whether the shared transportation vehicle is overloaded by comparing the real-time load weight with the first overload threshold.

[0052] The first overload threshold is an overload threshold determined based on a user weight model of the user.

[0053] The user weight model is a normal distribution model pre-built based on the user's historical weight records.

[0054] Among them, the historical weight record is the weight record measured by the user through shared transportation when the user used shared transportation in the past.

[0055] In a specific implementation, after the server obtains the real-time load weight transmitted back by the shared vehicle, the server can determine whether the shared vehicle is overloaded by comparing the numerical relationship between the real-time load weight and the first overload threshold.

[0056] The first overload threshold may be an overload threshold determined based on the user weight model, which is a normal distribution model constructed based on historical weight records of the user measured by the shared transportation vehicle when the user used the shared transportation vehicle in the past.

[0057] Specifically, when a user starts using a shared electric vehicle by scanning a code, the server can query the user weight model corresponding to the user in the database based on the user account that initiated the order; the server can determine the overload threshold that matches the weight feature based on the weight feature in the user weight model corresponding to the user.

[0058] Specifically, the user weight model can be a normal distribution model, and some graphical features of the normal distribution model (such as mean, variance, skewness, kurtosis, standard deviation, etc.) can be used as weight features to characterize the user's weight; based on the weight features, the server determines a first overload threshold that can be used to define whether the user has overload behavior.

[0059] Then, the server can compare the numerical relationship between the real-time load weight and the first overload threshold value, and when the server detects that the real-time load weight is greater than the first overload threshold value, the server determines that the shared vehicle is overloaded. When the server detects that the real-time load weight is less than or equal to the first overload threshold value, the server determines that the shared vehicle is not overloaded.

[0060] In actual applications, when the server detects that a shared vehicle is overloaded, the server can send an overload reminder instruction to the shared vehicle, and use the overload reminder instruction to control the shared vehicle to issue an overload reminder message (such as emitting a beep with a preset rhythm, playing an overload reminder voice, etc.). The overload reminder message reminds the user who is operating the shared vehicle that there is currently an overload, and reminds the user to pay attention to driving safety or riding safety, etc.

[0061] In the above-mentioned overload detection method for shared transportation, the real-time load weight of the shared transportation is obtained during the user's use of the shared transportation, and the real-time load weight is compared with a first overload threshold to determine whether the shared transportation is overloaded, wherein the first overload threshold is an overload threshold determined based on the user's weight model, and the user weight model is a normal distribution model pre-constructed based on the user's historical weight record, and the historical weight record is a weight record measured by the shared transportation when the user used the shared transportation in the past; in this way, the user's weight characteristics can be effectively and accurately characterized by the user weight model, and in the process of the user using the shared transportation, whether the real-time load weight representing the user's weight deviates significantly from the established user weight model can be detected in real time to determine whether the shared transportation is overloaded, thereby effectively determining whether the user is overloaded and avoiding the risk of misjudgment due to personal weight fluctuations or occasional weight bearing.

[0062] In an exemplary embodiment, the above method also includes: creating a user's weight database; the weight database is used to record multiple real-time load weight data records transmitted back by shared transportation vehicles as multiple weight records of the user; when the number of weight records in the weight database is equal to a preset number threshold, constructing a user weight model for the user based on the weight records stored in the weight database.

[0063] Among them, constructing a user weight model of the user according to the weight records stored in the weight database includes: determining the user's weight mean and weight standard deviation according to the weight records stored in the weight database; and using the weight mean and weight standard deviation as parameters of the user weight model to construct the user weight model.

[0064] In a specific implementation, when a user scans a code to use the shared transportation tool for the first time, the server can create at least one weight database corresponding to the user account that initiated the order with the user; the weight database records the multiple real-time load weight data records sent back by the shared transportation tool when the user uses the shared transportation tool, and uses them as multiple weight records of the user; specifically, whenever the server receives a data record carrying the real-time load weight uploaded by the in-vehicle intelligent central control of the shared transportation tool, the server will record the time when the data record is uploaded; then, the server can use the above data records to create a user historical weight data table {W1, W2, …, W i ,…,W n}, and the weight data recording schedule {T1, T2, …, T i ,…,T n}.

[0065] It should be understood that the sample data volume n recorded in the above user historical weight data table and the weight data recording schedule is the same, and the server can associate the user historical weight data table and the weight data recording schedule through the index i, that is, T i The sensor data obtained at the time point is W i , thereby building a weight database corresponding to the user.

[0066] Then, the server can detect the number of currently stored weight records; when the number of weight records in the weight database is equal to the preset number threshold, the server can construct a user weight model for the user based on the weight records stored in the weight database. In practical applications, the pre-examination number threshold can be set to 50.

[0067] Specifically, when the server detects that the number of weight records currently stored in the weight database reaches 50, the server can determine the user's historical weight data {W1, W2, ..., W i ,…,Wn} obeys normal distribution. Based on the above weight records, the server constructs a normal distribution model of historical weight records. The normal distribution model can be expressed as:

[0068]

[0069] Among them, μ prev is the average weight of historical weight records, is the standard deviation of historical weight records; n is the number of weight records stored in the weight database (i.e., the amount of data).

[0070] The average weight of the user μ prev The calculation method is expressed as:

[0071]

[0072] The standard deviation of the user's weight The calculation method is expressed as:

[0073]

[0074] In this way, the server can use the calculated weight mean and weight standard deviation as parameters of the user weight model to build a user weight model corresponding to the user.

[0075] The technical solution of this embodiment is to create a weight database of the user, which is used to record multiple real-time load weight data records transmitted back by the shared transportation vehicle as multiple weight records of the user; when the number of weight records in the weight database is equal to a preset number threshold, the user's weight mean and weight standard deviation are determined according to the weight records stored in the weight database; the weight mean and weight standard deviation are used as parameters of the user weight model to construct the user weight model, so that after the amount of stored user weight data reaches a certain level, a user weight model reflecting the weight characteristics of the user can be constructed based on the stored user weight data. Since a large number of data samples are accumulated, the user weight model has a certain reference value, which is conducive to effectively judging whether the shared transportation vehicle is overloaded based on the first overload threshold determined based on the user weight model in the future.

[0076] In an exemplary embodiment, when the number of weight records in the weight database is greater than a preset threshold value, the method further includes: whenever a new weight record is received, updating the parameters of the user weight model according to the new weight record; in the process of updating the parameters of the user weight model, determining the influence weight of the new weight record on the parameters of the user weight model according to the time interval between the new weight record and the previous weight record, and the number of weight records in the weight database.

[0077] In a specific implementation, when the number of weight records in the weight database is greater than a preset number threshold, each time the server receives a new weight record, the server can update the parameters of the user's weight model based on the new weight record. In the process of updating the parameters of the user's weight model, the server can obtain the time interval between the new weight record and the previous weight record, and based on the time interval and the number of weight records in the weight database, dynamically adjust the weight of the influence of the new weight record on the parameters of the user's weight model in the process of updating the parameters of the user's weight model based on the new weight record. In actual applications, the longer the time interval between the new weight record and the previous weight record, the smaller the weight of the influence of the new weight record on the parameters of the user's weight model.

[0078] The technical solution of this embodiment, whenever a new weight record is received, determines the influence weight of the new weight record on the parameters of the user's weight model according to the time interval between the new weight record and the previous weight record, and the number of weight records in the weight database, and updates the parameters of the user's weight model based on the influence weight and the new weight record, thereby realizing a dynamic weight adjustment mechanism, which can effectively weaken the influence of old data on the current normal distribution model, thereby strengthening the decision weight of recent data, and in the case of a large accumulation of data samples, can also improve the reference of the overall model by integrating historical data.

[0079] In an exemplary embodiment, the parameters of the user weight model include the user's mean weight and weight standard deviation, and the parameters of the user weight model are updated according to the new weight record, including: determining the weakness factor according to the number of weight records in the weight database according to a preset first mapping relationship; wherein the number of weight records in the weight database is negatively correlated with the value of the weakness factor; determining the weight coefficient according to the weakness factor and the time interval according to a preset second mapping relationship; the product of the weakness factor and the time interval is positively correlated with the weight coefficient; and adjusting the user's mean weight and weight standard deviation according to the weight coefficient and the new weight record to obtain a new mean weight and a new weight standard deviation, so as to update the parameters of the user weight model.

[0080] In a specific implementation, when the parameters of the user weight model include the user's mean weight and weight standard deviation, when the server updates the parameters of the user weight model according to new weight records, the server can use an exponential decay method to dynamically adjust the weight coefficient α, and use the weight coefficient α to update the normal distribution model.

[0081] Specifically, each time the server receives a new weight record, the server can calculate the time interval between the new weight record and the previous weight record according to the recording time of the new weight record, that is, the time step t. The calculation method of the time step t is:

[0082]

[0083] Among them, T i The i-th weight record of the user collected for the shared transportation.

[0084] Then, the server may determine the frailty factor λ according to the number of weight records in the weight database according to the preset first mapping relationship; in practical applications, the first mapping relationship may be expressed as:

[0085]

[0086] Among them, n refers to the number of weight records in the weight database (ie, the number of samples); it can be seen that the number of weight records n in the weight database is negatively correlated with the value of the frailty factor λ, and the value range of λ is (0.01, 0.1).

[0087] Then, the server can determine the weight coefficient according to the preset second mapping relationship, the attenuation factor and the time interval. In practical applications, the second mapping relationship can be expressed as:

[0088]

[0089] It can be seen that the product of the decay factor λ and the time interval t is positively correlated with the weight coefficient α(t); in other words, the larger the decay factor λ, the faster the weight coefficient of the historical weight data decays, and vice versa. The decay factor λ is negatively correlated with the sample size n, that is, as the number of times and duration of users using shared electric vehicles increases, the larger the value of n, the more sample data there is, the slower the weight of the historical weight data decays, and the more valuable the historical weight data is for reference.

[0090] At the same time, it can be seen from the second mapping relationship that the time interval t is also positively correlated with the weight coefficient α(t); in other words, the larger the time interval t is, the faster the weight coefficient (1-α(t)) of the historical weight data decays. In other words, if a user has not ridden a shared electric vehicle for a long time, the weight change of the user during this period may be large. If the historical weight data is used to determine whether the shared electric vehicle is overloaded, it may be easy to make a misjudgment. Therefore, by weakening the weight coefficient (1-α(t)) of the historical weight data, the reference of the latest real-time weight data in determining whether the shared electric vehicle is overloaded can be improved.

[0091] Then, the server can calculate the weight coefficient α(t) and the new weight record W current , adjust the user's weight mean and weight standard deviation to obtain a new weight mean and a new weight standard deviation to update the parameters of the user's weight model.

[0092] Among them, the new mean weight μ new It can be expressed as:

[0093]

[0094] New weight standard deviation It can be expressed as:

[0095]

[0096] It should be noted that the new mean weight μ new and the new standard deviation of weight The data is dynamically updated. Every time new data is received, the value of the weight coefficient α(t) is dynamically updated, and the new weight mean μ is updated by the weight coefficient α(t). new and the new standard deviation of weight The value of the user's historical weight data table {W1, W2, ..., W i ,…,W n}, and the weight data recording schedule {T1, T2, …, T i ,…,T n Every time a sample of} is added and the value of n is increased by 1, the mean weight and standard deviation of weight will be recalculated based on the last updated normal distribution model to achieve timely update of the user's weight model.

[0097] Through the above processing method, if the time interval between two weight records is too long, that is, the user has not ridden again for a long period of time after completing a ride, the reference value of the past weight records in determining whether it is overloaded will continue to decrease as the time interval increases; as the amount of data accumulates, the above algorithm reflects the negative correlation between the amount of data n and the attenuation factor λ, reflecting that the more historical data samples there are, the slower the decay of the historical data weight, and the overall normal distribution model is of reference value.

[0098] The technical solution of this embodiment determines the influence weight of the new weight record on the parameters of the user weight model during the updating of the user weight model by utilizing the above-mentioned first mapping relationship and the second mapping relationship; it can realize utilizing the time interval between the new weight record and the previous weight record, and the number of historical weight data in the weight database, to more reasonably determine the reference of the new weight data in determining whether the shared electric vehicle is overloaded; specifically, when the historical weight data does not have a certain scale, it can be considered that the historical weight data table has a low reference for the construction of the normal distribution, and therefore the weight of the real-time weight data for the construction of the normal distribution model can be increased; when the amount of historical weight data reaches a certain scale, it can be considered that the normal distribution model constructed by the historical weight data has a higher reference, and therefore the weight of the real-time weight data for the construction of the normal distribution model can be reduced, and the user weight model is continuously adjusted and updated by the above-mentioned dynamic weight adjustment mechanism, so that the user weight model can be used for accurate overload judgment.

[0099] At the same time, the dynamic adjustment weight mechanism provided by the present application can well balance the reference of the user's historical weight data and real-time weight data for constructing the user weight model of the user. By simultaneously referring to the historical weight data and the real-time weight data to construct a user weight model for overload judgment, the risk of misjudgment caused by personal weight fluctuations or occasional weight bearing of the user can be effectively avoided. When the amount of historical weight data reaches a certain scale, by increasing the weight of the historical weight data for the construction of the user weight model and reducing the weight of the real-time weight data for the construction of the normal distribution model, the reasonable reference value of the historical weight data can be effectively retained, ensuring that the constructed normal distribution model is both objective and efficient, thereby improving the accuracy and reliability of overload judgment using the normal distribution model.

[0100] In an exemplary embodiment, the method also includes: obtaining a second overload threshold when the number of weight records stored in the weight database is less than a preset number threshold; and determining whether the shared vehicle is overloaded by comparing the real-time load weight with the second overload threshold.

[0101] Among them, the second overload threshold is an overload threshold pre-configured by the supervision object of the shared transportation vehicle.

[0102] In actual applications, the server may be configured with a supervision system, which is used for supervision objects (eg, supervision users) to supervise the shared transportation vehicle.

[0103] For example, the supervising user may configure the specific value of the second overload threshold through the supervising system; in other words, the second overload threshold may refer to the maximum load limit W of the shared vehicle. max ; In the default state, the maximum load limit is W maxCan be set to 100kg.

[0104] In a specific implementation, the number of weight records stored in the weight database is less than the preset threshold. For example, when a user uses a shared vehicle for the first time and the weight database stores less than 50 weight records, the weight characteristics characterized by the normal distribution model constructed based on the currently stored weight records are often less referenceable because the number of samples of the user's weight records stored in the weight database is insufficient. In this case, the server can determine whether the shared vehicle is overloaded by comparing the real-time load weight with the second overload threshold pre-configured by the supervision object.

[0105] Specifically, when the server detects that the real-time load weight is greater than the second overload threshold, the server determines that the shared vehicle is overloaded. When the server detects that the real-time load weight is less than or equal to the second overload threshold, the server determines that the shared vehicle is not overloaded.

[0106] In actual applications, when the server detects that a shared vehicle is overloaded, the server can send an overload reminder instruction to the shared vehicle, and use the overload reminder instruction to control the shared vehicle to issue an overload reminder message (such as emitting a beep with a preset rhythm, playing an overload reminder voice, etc.). The overload reminder message reminds the user who is operating the shared vehicle that there is currently an overload, and reminds the user to pay attention to driving safety or riding safety, etc.

[0107] The technical solution of this embodiment is that when the number of weight records stored in the weight database is less than a preset number threshold, by comparing whether the real-time load weight of the shared vehicle exceeds a second overload threshold pre-configured by the supervisory object of the shared vehicle, even when the reference degree of the user weight model is low due to an insufficient number of user weight samples collected by the shared vehicle, it is still possible to effectively and stably identify whether the shared vehicle is overloaded.

[0108] In an exemplary embodiment, obtaining the first overload threshold includes: determining a method for calculating the upper limit of a preset confidence interval through a standard normal distribution table; processing the weight mean and weight standard deviation according to the upper limit calculation method to obtain an upper limit value of the confidence interval as the first overload threshold.

[0109] The parameters of the user weight model include the user's weight mean and weight standard deviation.

[0110] In a specific implementation, when the server obtains the first overload threshold, the server can determine the upper limit calculation method of the preset confidence interval through the standard normal distribution table. Taking the preset confidence interval as a 95% confidence interval as an example, the server can query the upper limit calculation method of the 95% confidence interval in the standard normal distribution table; in actual applications, the upper limit calculation method of the 95% confidence interval can be expressed as:

[0111]

[0112] Among them, CI refers to the first overload threshold (i.e. the upper limit of the confidence interval), refers to the new mean weight in the user's weight model. Refers to the new weight standard deviation in the user's weight model.

[0113] Then, the server can process the weight mean and weight standard deviation in the user weight model according to the above-mentioned upper limit calculation method to obtain the confidence interval upper limit value CI as the first overload threshold. Specifically, the server can substitute the weight mean and weight standard deviation into the above-mentioned upper limit calculation formula to obtain the confidence interval upper limit value. The server can determine whether the shared vehicle is overloaded by comparing the first overload threshold with the real-time load weight transmitted back by the shared vehicle.

[0114] The technical solution of this embodiment, in the process of obtaining the first overload threshold, determines the upper limit calculation method of the preset confidence interval from the standard normal distribution table, and processes the weight mean and weight standard deviation according to the upper limit calculation method, to obtain the upper limit value of the confidence interval as the basis for determining the first overload threshold, so that by configuring a specific confidence interval, it is possible to determine a first overload threshold that accurately represents the normal weight level of the user in combination with the normal distribution of weight data in the user weight model, and based on the first overload threshold, accurately judge whether the user's current weight deviates from the weight characteristics represented by the user's weight model.

[0115] In another embodiment, as shown in FIG. 3 , a method for detecting overload of a shared vehicle is provided, which is described by taking the method applied to the server in FIG. 1 as an example, and includes the following steps:

[0116] Step S302, when the user uses the shared transportation tool for the first time, a weight database of the user is created; the weight database is used to record multiple real-time load weight data records transmitted back by the shared transportation tool as multiple weight records of the user.

[0117] Step S304, when the number of weight records in the weight database is equal to the preset number threshold, determine the user's weight mean and weight standard deviation according to the weight records stored in the weight database.

[0118] Step S306, using the weight mean and weight standard deviation as parameters of the user weight model to construct the user weight model.

[0119] Step S308: Whenever a new weight record is received, the parameters of the user weight model are updated according to the new weight record.

[0120] Step S310, during the process of updating the parameters of the user weight model, the influence weight of the new weight record on the parameters of the user weight model is determined according to the time interval between the new weight record and the previous weight record and the number of weight records in the weight database.

[0121] Step S312, determining a method for calculating the upper limit of a preset confidence interval through a standard normal distribution table.

[0122] Step S314, according to the upper limit calculation method, the parameters of the user weight model including the weight mean and the weight standard deviation are processed to obtain the upper limit value of the confidence interval as the first overload threshold.

[0123] Step S316, determining whether the shared transportation vehicle is overloaded by comparing the real-time load weight with the first overload threshold.

[0124] It should be noted that the specific limitations of the above steps can be found in the specific limitations of the overload detection method for a shared vehicle mentioned above.

[0125] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0126] Based on the same inventive concept, the embodiment of the present application also provides an overload detection device for a shared vehicle for implementing the above-mentioned overload detection method for a shared vehicle. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the overload detection device for a shared vehicle provided below can refer to the above-mentioned limitations on the overload detection method for a shared vehicle, and will not be repeated here.

[0127] In an exemplary embodiment, as shown in FIG4 , an overload detection device for a shared vehicle is provided, comprising:

[0128] The acquisition module 410 is used to acquire the real-time load weight of the shared transportation tool when the user uses the shared transportation tool;

[0129] A judgment module 420 is used to obtain a first overload threshold value, and judge whether the shared transportation vehicle is overloaded by comparing the real-time load weight with the first overload threshold value;

[0130] Among them, the first overload threshold is an overload threshold determined based on the user weight model of the user, and the user weight model is a normal distribution model pre-constructed based on the user's historical weight record, and the historical weight record is a weight record measured by the shared transportation vehicle when the user used the shared transportation vehicle in the past.

[0131] In one embodiment, the device further comprises:

[0132] A storage module, used to create a weight database of the user; the weight database is used to record multiple data records of the real-time load weight transmitted back by the shared transportation vehicle as multiple weight records of the user;

[0133] a determination module, configured to determine the mean weight and the standard deviation of the weight of the user according to the weight records stored in the weight database when the number of weight records in the weight database is equal to a preset number threshold;

[0134] A construction module is used to use the weight mean and the weight standard deviation as parameters of the user weight model to construct the user weight model.

[0135] In one of the embodiments, when the number of weight records in the weight database is greater than the preset number threshold, the device further includes:

[0136] An updating module, configured to update the parameters of the user weight model according to the new weight record whenever a new weight record is received;

[0137] In the process of updating the parameters of the user weight model, the influence weight of the new weight record on the parameters of the user weight model is determined according to the time interval between the new weight record and the previous weight record, and the number of weight records in the weight database.

[0138] In one embodiment, the parameters of the user weight model include the user's mean weight and weight standard deviation, and the update module is specifically used to determine the weakness factor according to a preset first mapping relationship and the number of weight records in the weight database; the number of weight records in the weight database is negatively correlated with the value of the weakness factor; according to a preset second mapping relationship, the weight coefficient is determined according to the weakness factor and the time interval; the product of the weakness factor and the time interval is positively correlated with the weight coefficient; according to the weight coefficient and the new weight record, the user's mean weight and weight standard deviation are adjusted to obtain a new mean weight and a new weight standard deviation, so as to update the parameters of the user weight model.

[0139] In one embodiment, the device further comprises:

[0140] A threshold query module, used to obtain a second overload threshold when the number of weight records stored in the weight database is less than the preset number threshold; the second overload threshold is an overload threshold pre-configured by the supervision object of the shared transportation vehicle;

[0141] The detection module is used to determine whether the shared transportation vehicle is overloaded by comparing the real-time load weight with the second overload threshold.

[0142] In one embodiment, the judgment module is specifically used to determine a method for calculating an upper limit of a preset confidence interval through a standard normal distribution table; process the weight mean and the weight standard deviation according to the upper limit calculation method to obtain an upper limit value of the confidence interval as the first overload threshold.

[0143] Each module in the above-mentioned overload detection device for a shared vehicle can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0144] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG5. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store XX data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for detecting overload of a shared vehicle is implemented.

[0145] Those skilled in the art will understand that the structure shown in FIG. 5 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0146] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above-mentioned method for detecting overload of a shared vehicle. The steps of the method for detecting overload of a shared vehicle here may be the steps of the method for detecting overload of a shared vehicle in each of the above-mentioned embodiments.

[0147] In one embodiment, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the processor executes the steps of the above-mentioned method for detecting overload of a shared vehicle. The steps of the method for detecting overload of a shared vehicle here may be the steps of the method for detecting overload of a shared vehicle in each of the above-mentioned embodiments.

[0148] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, causes the processor to execute the steps of the above-mentioned method for detecting overload of a shared vehicle. The steps of the method for detecting overload of a shared vehicle here may be the steps of the method for detecting overload of a shared vehicle in each of the above-mentioned embodiments.

[0149] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0150] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0151] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0152] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for detecting overload of a shared vehicle, characterized in that: The method comprises: When a user uses a shared transportation tool, obtaining the real-time load weight of the shared transportation tool; Obtaining a first overload threshold, and determining whether the shared transportation vehicle is overloaded by comparing the real-time load weight with the first overload threshold; Among them, the first overload threshold is an overload threshold determined based on the user weight model of the user, and the user weight model is a normal distribution model pre-constructed based on the user's historical weight record, and the historical weight record is a weight record measured by the shared transportation vehicle when the user used the shared transportation vehicle in the past.

2. The method according to claim 1, characterized in that The method further comprises: Creating a weight database of the user; the weight database is used to record the multiple data records of the real-time load weight transmitted back by the shared transportation vehicle as multiple weight records of the user; When the number of weight records in the weight database is equal to a preset number threshold, determining the weight mean and weight standard deviation of the user according to the weight records stored in the weight database; The weight mean and the weight standard deviation are used as parameters of the user weight model to construct the user weight model.

3. The method according to claim 2, characterized in that When the number of weight records in the weight database is greater than the preset number threshold, the method further includes: Whenever a new weight record is received, the parameters of the user weight model are updated according to the new weight record; In the process of updating the parameters of the user weight model, the influence weight of the new weight record on the parameters of the user weight model is determined according to the time interval between the new weight record and the previous weight record, and the number of weight records in the weight database.

4. The method according to claim 3, characterized in that The parameters of the user weight model include the user's weight mean and weight standard deviation, and the updating of the parameters of the user weight model according to the new weight record includes: According to a preset first mapping relationship, a frailty factor is determined according to the number of weight records in the weight database; the number of weight records in the weight database is negatively correlated with the value of the frailty factor; According to a preset second mapping relationship, a weight coefficient is determined according to the attenuation factor and the time interval; the product of the attenuation factor and the time interval is positively correlated with the weight coefficient; According to the weight coefficient and the new weight record, the user's weight mean and weight standard deviation are adjusted to obtain a new weight mean and a new weight standard deviation, so as to update the parameters of the user's weight model.

5. The method according to claim 2, characterized in that: The method further comprises: When the number of weight records stored in the weight database is less than the preset number threshold, obtaining a second overload threshold; the second overload threshold is an overload threshold pre-configured by the supervision object of the shared transportation vehicle; By comparing the real-time load weight with the second overload threshold, it is determined whether the shared transportation vehicle is overloaded.

6. The method according to any one of claims 1 to 5, characterized in that: The parameters of the user weight model include the user's weight mean and weight standard deviation. The obtaining of the first overload threshold comprises: Determine the calculation method of the upper limit of the preset confidence interval through the standard normal distribution table; The weight mean and the weight standard deviation are processed according to the upper limit calculation method to obtain an upper limit value of a confidence interval as the first overload threshold.

7. An overload detection device for a shared vehicle, characterized in that: include: An acquisition module, used to acquire the real-time load weight of a shared transportation vehicle when a user uses the shared transportation vehicle; A judgment module, configured to obtain a first overload threshold value, and judge whether the shared transportation vehicle is overloaded by comparing the real-time load weight with the first overload threshold value; Among them, the first overload threshold is an overload threshold determined based on the user weight model of the user, and the user weight model is a normal distribution model pre-constructed based on the user's historical weight record, and the historical weight record is a weight record measured by the shared transportation vehicle when the user used the shared transportation vehicle in the past.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images