Big data analysis method and platform for short message sending success rate of multi-region Internet of Vehicles

Abstract

The invention relates to the technical field of mobile communication, and discloses a big data analysis method and platform for a multi-area Internet of Vehicles short message sending success rate, and the method comprises the steps: determining a corresponding service provider based on the related information of a user, constructing M initial sending channels based on M third-party platforms and current state information, and sending the M initial sending channels to a server; respectively predicting based on the M initial sending channels to obtain a corresponding first success rate, screening the M initial sending channels according to the first success rate, finally respectively predicting the S final sending channels to obtain a corresponding second success rate, and taking the final sending channel corresponding to the maximum second success rate as a target sending channel; according to the method, the target sending channel is dynamically determined through real-time prediction and optimal selection, and the highest sending success rate is ensured, so that the multi-area transmission efficiency, success rate and stability of short messages transmitted from domestic manufacturers to overseas users are remarkably improved, and meanwhile, the resource consumption is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the field of mobile communication technology, and more specifically, to a big data analysis method and platform for the success rate of short message sending in multi-region Internet of Vehicles. Background Art

[0002] Exported vehicles are usually equipped with intelligent vehicle systems, including remote control, navigation updates, system notifications and other functions. In order to support these services, the vehicle system needs to exchange information through text messages, such as sending remote control commands, pushing emergency notifications or updating vehicle status. The effectiveness of this information interaction directly affects the user experience and brand competitiveness. However, there are many technical challenges in the process of sending text messages from domestic manufacturers to overseas users. Since it involves cross-border communications, text messages need to pass through domestic text message service providers, and then they will complete the delivery through third-party platforms in the area where overseas users are located. In this process, the reliability of successful delivery of text messages is affected by many factors. Although the existing technology discloses relevant content about the success rate of text message sending, there are still certain problems.

[0003] In the prior art, for example, a patent application with publication number CN117041893A discloses a method and system for sending international text messages using cloud computing technology. Cloud computing technology is used to integrate multiple international text message receiving gateways, sending gateways, and message queue clusters, and is equipped with a load balancer and a monitoring center to achieve task allocation and parallel processing. This design improves the efficiency, stability, and security of international text message sending.

[0004] Although the above-mentioned existing technologies use cloud computing to improve the efficiency of sending international SMS, since SMS needs to be transmitted through domestic SMS service providers and then through third-party platforms in the area where overseas users are located, SMS service providers and regional third-party platforms become key factors affecting the SMS transmission effect. In addition, the existing technology is still unable to dynamically select the optimal SMS sending channel, making it difficult to effectively improve the success rate of SMS sending.

[0005] In view of this, the present invention proposes a big data analysis method and platform for the success rate of SMS sending in multiple regions of Internet of Vehicles to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a big data analysis method and platform for the success rate of SMS sending in multiple regions of Internet of Vehicles.

[0007] To achieve the above object, the present invention provides the following technical solutions: First, a big data analysis method for the success rate of SMS messages sent in multiple regions of Internet of Vehicles is provided, including: Obtain user-related information and current status information corresponding to the user to be sent, and determine the corresponding service provider based on the user-related information; Obtain M third-party platforms corresponding to the service provider, construct M initial sending channels based on the M third-party platforms and current state information, and perform predictions based on the M initial sending channels to obtain corresponding first success rates; According to the first success rate, M initial sending channels are screened to obtain N intermediate sending channels, the N intermediate sending channels are clustered to obtain S final sending channels, the S final sending channels are predicted separately to obtain corresponding second success rates, and the final sending channel corresponding to the largest second success rate is used as the target sending channel, where N≤M.

[0008] Furthermore, the method for determining the corresponding service provider based on the user-related information includes: Based on the information of the area where they are located, Q initial suppliers are determined, and the corresponding communication service level is determined according to the information of the vehicles to which they belong. Based on the communication service level, P intermediate suppliers are screened out from the Q initial suppliers, and the historical communication success rates corresponding to the P intermediate suppliers are calculated according to the historical communication records. The intermediate supplier corresponding to the maximum historical communication success rate is selected as the service provider.

[0009] Furthermore, the method for constructing M initial sending channels based on M third-party platforms and current status information includes: Traverse M third-party platforms in turn, take the third-party platform, current time zone and current device as nodes, and take the current load information as the edge between nodes, so as to build a sending channel graph, and use the sending channel graph as the initial sending channel.

[0010] Further, a method for performing predictions based on the M initial sending channels to obtain a corresponding first success rate includes: Inputting the M initial sending channels into a pre-built first prediction model in sequence to obtain a corresponding first success rate; The construction method of the first prediction model includes: Acquire a sample data set, wherein the sample data set includes a historical initial sending channel and a historical first success rate; Divide the sample data set into a sample training set and a sample test set, and build a regression network; The historical initial transmission channel in the sample training set is used as input data of the regression network, and the historical first success rate in the sample training set is used as output data of the regression network, and the regression network is trained to obtain an initial regression network for predicting the first success rate; The initial regression network is tested using a sample test set, and the initial regression network with an output smaller than a preset error value is used as the first prediction model.

[0011] Furthermore, the method of screening the M initial sending channels according to the first success rate to obtain the N intermediate sending channels includes: Traverse M initial sending channels, obtain the load stability data and area coverage data corresponding to the initial sending channels, calculate the load stability value according to the load stability data, calculate the area coverage value according to the area coverage data, determine the real-time comprehensive value based on the first success rate, the load stability value and the area coverage value, eliminate the initial sending channels whose real-time comprehensive values ​​are less than the preset comprehensive threshold, so as to obtain N intermediate sending channels.

[0012] Furthermore, the load stability data includes an average response delay, a bandwidth usage value, and a maximum fluctuation amplitude. The method for calculating the load stability value according to the load stability data includes: LSV= ; Where LSV is the load stability value, is the average response delay, is the bandwidth usage value, is the maximum fluctuation range, is the hyperbolic cosine function, is the hyperbolic sine function, is a logarithmic function with base e, is an exponential function with base e, , are all weight factors.

[0013] Furthermore, the area coverage data includes an area coverage ratio, a supporting equipment ratio, and a specific compliance value. The method for calculating the area coverage value according to the area coverage data includes: RCV= ; Where RCV is the regional coverage value, is the area coverage ratio, To support the equipment ratio, For a specific matching value, is the inverse cotangent function, , are all constants greater than 0.

[0014] Furthermore, a method for clustering N intermediate sending channels to obtain S final sending channels includes: According to the first success rate, load stability value and area coverage value, N intermediate sending channels are clustered to obtain S intermediate sending channel combinations, and the intermediate sending channel with the largest real-time comprehensive value is selected from the S intermediate sending channel combinations as the final sending channel, thereby obtaining S final sending channels.

[0015] In the second aspect, a big data analysis platform for the success rate of SMS messages sent in multiple regions of the Internet of Vehicles is provided, which is used to implement the big data analysis method for the success rate of SMS messages sent in multiple regions of the Internet of Vehicles, including: The first processing module is used to obtain user-related information and current status information corresponding to the user to be sent, and determine the corresponding service provider based on the user-related information; The second processing module is used to obtain M third-party platforms corresponding to the service provider, construct M initial sending channels based on the M third-party platforms and current state information, and perform predictions based on the M initial sending channels to obtain corresponding first success rates; Channel selection module: used to screen M initial sending channels according to the first success rate to obtain N intermediate sending channels, cluster the N intermediate sending channels to obtain S final sending channels, predict the S final sending channels separately to obtain the corresponding second success rate, and use the final sending channel corresponding to the largest second success rate as the target sending channel, wherein N≤M.

[0016] In a third aspect, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned big data analysis method for the success rate of SMS sending in multiple-region Internet of Vehicles when executing the computer program.

[0017] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed, the big data analysis method for the success rate of SMS sending in multiple regions of Internet of Vehicles is implemented.

[0018] Compared with the prior art, the present invention has the following beneficial effects: The present invention first determines the corresponding service provider based on user-related information, then constructs M initial sending channels based on M third-party platforms and current status information, performs respective predictions based on the M initial sending channels to obtain a corresponding first success rate, and finally screens the M initial sending channels according to the first success rate to obtain N intermediate sending channels, clusters the N intermediate sending channels to obtain S final sending channels, performs respective predictions on the S final sending channels to obtain a corresponding second success rate, and uses the final sending channel corresponding to the largest second success rate as the target sending channel. In this way, the present invention dynamically determines the target sending channel through real-time prediction and optimization selection to ensure that it has the highest sending success rate, thereby significantly improving the multi-region transmission efficiency, success rate and stability of short messages from domestic manufacturers to overseas users, while effectively reducing resource consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1It is a flow chart of the big data analysis method of the success rate of SMS sending in multiple regions of Internet of Vehicles in the present invention; Figure 2 It is a structural schematic diagram of a big data analysis platform for the success rate of SMS sending in multiple regions of Internet of Vehicles in the present invention; Figure 3 A flow chart of a method for determining a corresponding service provider based on user-related information in the present invention; Figure 4 It is a flowchart of a method for screening M initial sending channels according to a first success rate in the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Example 1 See also Figure 1 As shown, this embodiment discloses a big data analysis method for the success rate of SMS sending in multiple regions of Internet of Vehicles, including: S10: Obtaining user-related information and current status information corresponding to the user to be sent, and determining a corresponding service provider based on the user-related information; In this embodiment, the user to be sent may be a foreign user. It is understandable that since the export business of domestic cars has covered many countries and regions, these exported vehicles are usually equipped with intelligent car systems to provide users with rich online services. In order to support these services, the car system needs to interact with information through text messages, and usually the manufacturer is in China, so it is necessary to ensure the success rate of text message sending, so as to improve the communication efficiency between the two parties.

[0022] In this embodiment, user-related information includes area information, vehicle information and historical communication records. The area information refers to information related to the geographical location and communication environment of the user to be sent, for example, the country, region or city where the user to be sent is located, the time zone of the user's area and specific requirements for SMS content, signature format or sending frequency, to ensure that the SMS is not blocked or intercepted; and the vehicle information refers to detailed information related to the vehicle purchased by the user to be sent from the manufacturer. The vehicle information may include the vehicle brand, vehicle system version and additional service content. The additional service content refers to the value-added services selected or subscribed by the user to be sent when purchasing the vehicle from the manufacturer, such as navigation update service and personalized notification service; historical communication records refer to the historical SMS interaction data between the user to be sent and the manufacturer. The historical communication records include at least the number of successful communications and the number of failed retries. The number of failed retries refers to the number of times the system retries to ensure successful delivery of the message due to the failure of the initial sending of the SMS during the historical SMS interaction process.

[0023] like Figure 3 As shown, the method for determining the corresponding service provider based on user-related information includes: Based on the information of the area where they are located, Q initial suppliers are determined, and the corresponding communication service level is determined according to the information of the vehicles to which they belong. Based on the communication service level, P intermediate suppliers are screened out from the Q initial suppliers, and the historical communication success rates corresponding to the P intermediate suppliers are calculated according to the historical communication records. The intermediate supplier corresponding to the maximum historical communication success rate is selected as the service provider.

[0024] It should be noted that the above-mentioned suppliers refer to suppliers that provide domestic SMS services, such as Tencent Cloud SMS Service, Alibaba Cloud SMS Service, Huawei Cloud SMS Service and Ronglian Cloud Communication, etc. Determining Q initial suppliers based on regional information refers to screening out domestic SMS service providers that can cover the area and have relevant service capabilities based on information related to the geographical location and communication environment of the users to be sent (such as the country, region or city where the users are located). For example, Tencent Cloud SMS Service has a higher coverage rate in North America, while Alibaba Cloud SMS Service has advantages in Southeast Asia.

[0025] Generally, the communication service level refers to the quality and priority of the manufacturer's communication service enjoyed by the user to be sent. It is understandable that, for example, the higher the price of the vehicle, the higher the communication service level, and the user can enjoy better communication services. It is understandable that the cost of providing services by each supplier is different. Therefore, this embodiment selects the supplier with the highest cost performance through the communication service level, and optimizes the service cost while meeting the communication service level requirements.

[0026] Methods for calculating the historical communication success rates of P intermediate suppliers based on historical communication records include: HCR= ; Where HCR is the historical communication success rate, is the number of successful communications, is the number of failed retries, , are weight factors, and .

[0027] This embodiment simplifies the complexity of supplier selection through a step-by-step screening and progressive approach (from Q initial suppliers to P intermediate suppliers, and then to the final selected service provider), allowing the system to quickly and efficiently determine the optimal service provider.

[0028] S20: Acquire M third-party platforms corresponding to the service provider, construct M initial sending channels based on the M third-party platforms and current state information, and perform predictions based on the M initial sending channels to obtain corresponding first success rates; It is understandable that the third-party platform refers to the local SMS gateway or operator responsible for delivering SMS from domestic service providers to the overseas users' areas. These third-party platforms usually have communication resources and network coverage capabilities in the target area and can complete the localized delivery of SMS, such as Twilio, Nexmo, AT&T or Vodafone.

[0029] It should be added that the current status information includes the current time zone, the current device and the current load information. The current time zone refers to the standard time offset or local time of the area where the user to be sent is located. The current device refers to the real-time status and capabilities of the user device (such as the vehicle system), such as whether the vehicle system is currently connected to the network or whether the vehicle system is in normal working mode or low-power sleep mode. The current load information refers to the real-time usage status of the SMS sending system or channel. It can be understood that the current device information and the current load information can be obtained through a third-party platform or the remote communication module of the vehicle system. Taking the current device information as an example, the method of obtaining the current device information can be that the third-party platform supports sending detection SMS or Ping signals to confirm the online status or receiving capability of the vehicle system.

[0030] The method for constructing M initial sending channels based on M third-party platforms and current status information includes: Traverse M third-party platforms in turn, take the third-party platform, current time zone and current device as nodes, and take the current load information as the edge between nodes, so as to build a sending channel graph, and use the sending channel graph as the initial sending channel.

[0031] It should be noted that using the third-party platform, current time zone and current device as nodes to represent the abstract representation of the key participating elements in the SMS sending process is used to construct a sending channel diagram. By representing these elements as nodes, the initial sending channel can intuitively display the logical relationship between different elements in the SMS sending process, and at the same time provide a structured analysis basis for subsequent success rate prediction. Using the current load information as the edge between nodes represents the real-time communication status between the key elements in the SMS sending channel. For example, the edge between the third-party platform and the current time zone represents the SMS sending load and communication efficiency of the third-party platform in the current time zone, and the edge between the current time zone and the current device represents the communication availability and receiving efficiency of the current device in the current time zone, such as the matching degree of the current device's active time or the device's receiving capability.

[0032] In this embodiment, the edge between the current time zone and the current device represents the above factors. The sending channel graph can reflect the feasibility and success rate of the current device receiving SMS in the current time zone, and further provide a quantitative basis for channel optimization and sending path selection.

[0033] The method of performing predictions based on the M initial transmission channels to obtain the corresponding first success rate includes: The M initial sending channels are sequentially input into a pre-built first prediction model to obtain a corresponding first success rate.

[0034] The construction method of the first prediction model includes: Acquire a sample data set, wherein the sample data set includes a historical initial sending channel and a historical first success rate; Divide the sample data set into a sample training set and a sample test set, and build a regression network; The historical initial transmission channel in the sample training set is used as input data of the regression network, and the historical first success rate in the sample training set is used as output data of the regression network, and the regression network is trained to obtain an initial regression network for predicting the first success rate; The initial regression network is tested using a sample test set, and the initial regression network with an output smaller than a preset error value is used as the first prediction model. The initial regression network is a deep neural network model.

[0035] It should be added that the above sample data set is obtained by technicians in this field through experiments. For example, in the European region, the third-party platform is Twilio, the current time zone is GMT+2, the current device status is online, and the current load information is 50%. The domestic manufacturer sends 100 text messages to users in the European region. When 90 of them arrive successfully, the first success rate can be 90%.

[0036] This embodiment first screens service providers to narrow the initial scope to domestic suppliers with high reliability and success rate, and then further uses M third-party platforms of these suppliers and current status information to build an initial sending channel, thereby ensuring the efficiency and pertinence of the sending path. This sequential combination enables the initial sending channel to simultaneously consider the supplier's historical data and current real-time communication conditions, thereby improving the success rate of SMS sending.

[0037] S30: screening the M initial sending channels according to the first success rate to obtain N intermediate sending channels, clustering the N intermediate sending channels to obtain S final sending channels, respectively predicting the S final sending channels to obtain corresponding second success rates, and taking the final sending channel corresponding to the maximum second success rate as the target sending channel, wherein N≤M; like Figure 4 As shown, the method of screening M initial sending channels according to the first success rate to obtain N intermediate sending channels includes: Traverse M initial sending channels, obtain the load stability data and area coverage data corresponding to the initial sending channels, calculate the load stability value according to the load stability data, calculate the area coverage value according to the area coverage data, determine the real-time comprehensive value based on the first success rate, the load stability value and the area coverage value, eliminate the initial sending channels whose real-time comprehensive values ​​are less than the preset comprehensive threshold, so as to obtain N intermediate sending channels.

[0038] In this embodiment, the load stability value represents the load fluctuation degree of the initial sending channel, and the regional coverage value represents the adaptability of the initial sending channel to the area where the target user is located. It is not difficult to understand that this embodiment does not use the first success rate as the only criterion for screening the initial sending channel. The purpose of doing so is to comprehensively consider the multi-dimensional performance of the initial sending channel to improve the overall reliability and adaptability of the intermediate sending channel. Specifically, although the first success rate can reflect the instantaneous sending effect of the channel, it cannot fully measure the long-term stability of the channel. Domestic manufacturers and foreign users need to maintain continuous communication and introduce regional coverage values ​​to ensure that the screened intermediate sending channels have better communication adaptability to the target user's area.

[0039] Generally, load stability data includes average response delay, bandwidth utilization value and maximum fluctuation amplitude. Average response delay refers to the average time delay from the initiation of SMS sending request to the successful sending of SMS in the initial sending channel within the historical time period. Bandwidth utilization value refers to the ratio of bandwidth occupied by the initial sending channel within the historical time period to the total available bandwidth. Maximum fluctuation amplitude refers to the maximum fluctuation amplitude of the channel load of the initial sending channel within the historical time period, that is, the fluctuation range of channel performance. The historical time period can be the previous several months or the previous several weeks, and this embodiment is not limited to this.

[0040] Methods for calculating the load stability value based on the load stability data include: LSV= ; Where LSV is the load stability value, is the average response delay, is the bandwidth usage value, is the maximum fluctuation range, is the hyperbolic cosine function, is the hyperbolic sine function, is a logarithmic function with base e, is an exponential function with base e, , are all weight factors.

[0041] It can be understood that, taking the average response delay and bandwidth utilization value as an example, when the average response delay is larger, it indicates that the average time from the initiation of the sending request to the successful sending of the text message of the initial sending channel becomes longer. Since the higher average response delay may be caused by excessive load, insufficient resources or reduced network transmission efficiency, when the bandwidth utilization value is larger, it indicates that the bandwidth resources of the initial sending channel are close to saturation and the remaining available bandwidth is small, which may cause resource contention and network congestion. Therefore, it also reflects the increased instability of the initial sending channel. Therefore, from the above content, it can be seen that in this embodiment, the larger the load stability value, the stronger the stability of the initial sending channel in transmitting text messages.

[0042] Generally, regional coverage data includes regional coverage ratio, supported device ratio and specific compliance value. The regional coverage ratio refers to the ratio of the network range covered by the initial sending channel in the target area to the overall network coverage range of the target area. For example, there are 10 major network operators in the target area, and the initial sending channel covers 8 of them, then the regional coverage ratio is 80%. The supported device ratio refers to the ratio of the number of user devices supported by the initial sending channel to the total number of all user devices in the target area. For example, there are 1,000 vehicle system devices in the target area, and the initial sending channel supports 900 of them, then the supported device ratio is 90%. The specific compliance value refers to the ratio of the initial sending channel's support for specific communication requirements in the target area (such as SMS content format, signature specifications, sending frequency restrictions, etc.). For example, specific communication requirements include supporting the language required by the target area, complying with the target area's legal requirements for corporate logos, signature locations or formats, etc.

[0043] Methods for calculating area coverage values ​​based on area coverage data include: RCV= ; Where RCV is the regional coverage value, is the area coverage ratio, To support the equipment ratio, For a specific matching value, is the inverse cotangent function, , are all constants greater than 0.

[0044] It should be noted that, taking the regional coverage ratio and the supporting device ratio as examples, the larger the regional coverage ratio, the wider the network support range of the initial sending channel for the target area where the user to be sent is located, and the stronger the adaptability. Similarly, the larger the supporting device ratio, the higher the compatibility of the initial sending channel for the user equipment in the target area where the user to be sent is located, and the stronger the adaptability. Therefore, from the above content, it can be seen that the larger the regional coverage value in this embodiment, the greater the service availability, reliability and compliance of the initial sending channel for the target area where the user to be sent is located.

[0045] It should be supplemented that the method for determining the real-time comprehensive value based on the first success rate, load stability value and regional coverage value may be to weightedly sum the first success rate, load stability value and regional coverage value, and the weight factors are all greater than 0. The real-time comprehensive value obtained in this way can reflect the comprehensive performance of the initial sending channel, including the overall performance of the instant sending effect, transmission stability and target area adaptability. Therefore, the larger the real-time comprehensive value, the stronger the comprehensive performance of the initial sending channel.

[0046] The method of clustering N intermediate sending channels to obtain S final sending channels includes: According to the first success rate, load stability value and area coverage value, N intermediate sending channels are clustered to obtain S intermediate sending channel combinations, and the intermediate sending channel with the largest real-time comprehensive value is selected from the S intermediate sending channel combinations as the final sending channel, thereby obtaining S final sending channels.

[0047] It can be understood that clustering N intermediate sending channels based on the first success rate means dividing the intermediate sending channels with similar first success rates into the same cluster according to the first success rates of the intermediate sending channels, and the same applies to load stability values ​​and regional coverage values. The purpose of this is to cluster the N intermediate sending channels so that the intermediate sending channels in the same intermediate sending channel combination have similar performance in terms of the first success rate, load stability or regional adaptability, which helps to select the best performing intermediate sending channel among the same channels. The clustering method can be K-Means clustering or hierarchical clustering, which is not limited to this in this embodiment.

[0048] The method of respectively predicting the S final transmission channels to obtain the corresponding second success rate includes: The S final sending channels are sequentially input into the pre-built second prediction model to obtain a corresponding second success rate.

[0049] It can be understood that the construction method of the second prediction model is the same as the construction method of the first prediction model, except that the input data in the training process is changed to the historical final sending channel, and the output data in the training process is changed to the historical second success rate. This embodiment does not go into details about this.

[0050] This embodiment first determines the corresponding service provider based on user-related information, then constructs M initial sending channels based on M third-party platforms and current status information, performs separate predictions based on the M initial sending channels, and obtains a corresponding first success rate, and finally screens the M initial sending channels according to the first success rate to obtain N intermediate sending channels, clusters the N intermediate sending channels to obtain S final sending channels, and performs separate predictions on the S final sending channels to obtain a corresponding second success rate, and uses the final sending channel corresponding to the largest second success rate as the target sending channel. In this way, this embodiment dynamically determines the target sending channel through real-time prediction and optimization selection to ensure that it has the highest sending success rate, thereby significantly improving the multi-region transmission efficiency, success rate and stability of SMS from domestic manufacturers to overseas users, while effectively reducing resource consumption.

[0051] Example 2 See also Figure 2 As shown, based on the same inventive concept, this embodiment discloses a big data analysis platform for the success rate of SMS sending in multiple regions of the Internet of Vehicles. For details not provided in this embodiment, please refer to the description of the relevant part in Embodiment 1. The big data analysis platform for the success rate of SMS sending in multiple regions of the Internet of Vehicles includes: The first processing module is used to obtain user-related information and current status information corresponding to the user to be sent, and determine the corresponding service provider based on the user-related information; In this embodiment, the user to be sent may be a foreign user. It is understandable that since the export business of domestic cars has covered many countries and regions, these exported vehicles are usually equipped with intelligent car systems to provide users with rich online services. In order to support these services, the car system needs to interact with information through text messages, and usually the manufacturer is in China, so it is necessary to ensure the success rate of text message sending, so as to improve the communication efficiency between the two parties.

[0052] Methods for determining the corresponding service provider based on user-related information include: Based on the information of the area where they are located, Q initial suppliers are determined, and the corresponding communication service level is determined according to the information of the vehicles to which they belong. Based on the communication service level, P intermediate suppliers are screened out from the Q initial suppliers, and the historical communication success rates corresponding to the P intermediate suppliers are calculated according to the historical communication records. The intermediate supplier corresponding to the maximum historical communication success rate is selected as the service provider.

[0053] Methods for calculating the historical communication success rates of P intermediate suppliers based on historical communication records include: HCR= ; Where HCR is the historical communication success rate, is the number of successful communications, is the number of failed retries, , are weight factors, and .

[0054] The second processing module is used to obtain M third-party platforms corresponding to the service provider, construct M initial sending channels based on the M third-party platforms and current state information, and perform predictions based on the M initial sending channels to obtain corresponding first success rates; It is understandable that the third-party platform refers to the local SMS gateway or operator responsible for delivering SMS from domestic service providers to the overseas users' areas. These third-party platforms usually have communication resources and network coverage capabilities in the target area and can complete the localized delivery of SMS, such as Twilio, Nexmo, AT&T or Vodafone.

[0055] The method for constructing M initial sending channels based on M third-party platforms and current status information includes: Traverse M third-party platforms in turn, take the third-party platform, current time zone and current device as nodes, and take the current load information as the edge between nodes, so as to build a sending channel graph, and use the sending channel graph as the initial sending channel.

[0056] The method of performing predictions based on the M initial transmission channels to obtain the corresponding first success rate includes: The M initial sending channels are sequentially input into a pre-built first prediction model to obtain a corresponding first success rate.

[0057] The construction method of the first prediction model includes: Acquire a sample data set, wherein the sample data set includes a historical initial sending channel and a historical first success rate; Divide the sample data set into a sample training set and a sample test set, and build a regression network; The historical initial transmission channel in the sample training set is used as input data of the regression network, and the historical first success rate in the sample training set is used as output data of the regression network, and the regression network is trained to obtain an initial regression network for predicting the first success rate; The initial regression network is tested using a sample test set, and the initial regression network with an output smaller than a preset error value is used as the first prediction model. The initial regression network is a deep neural network model.

[0058] Channel selection module: used to screen M initial sending channels according to the first success rate to obtain N intermediate sending channels, cluster the N intermediate sending channels to obtain S final sending channels, predict the S final sending channels respectively to obtain the corresponding second success rate, and use the final sending channel corresponding to the largest second success rate as the target sending channel, where N≤M; The method of screening the M initial sending channels according to the first success rate to obtain the N intermediate sending channels includes: Traverse M initial sending channels, obtain the load stability data and area coverage data corresponding to the initial sending channels, calculate the load stability value according to the load stability data, calculate the area coverage value according to the area coverage data, determine the real-time comprehensive value based on the first success rate, the load stability value and the area coverage value, eliminate the initial sending channels whose real-time comprehensive values ​​are less than the preset comprehensive threshold, so as to obtain N intermediate sending channels.

[0059] Methods for calculating the load stability value based on the load stability data include: LSV= ; Where LSV is the load stability value, is the average response delay, is the bandwidth usage value, is the maximum fluctuation range, is the hyperbolic cosine function, is the hyperbolic sine function, is a logarithmic function with base e, is an exponential function with base e, , are all weight factors.

[0060] Methods for calculating area coverage values ​​based on area coverage data include: RCV= ; Where RCV is the regional coverage value, is the area coverage ratio, To support the equipment ratio, For a specific matching value, is the inverse cotangent function, , are all constants greater than 0.

[0061] The method of clustering N intermediate sending channels to obtain S final sending channels includes: According to the first success rate, load stability value and area coverage value, N intermediate sending channels are clustered to obtain S intermediate sending channel combinations, and the intermediate sending channel with the largest real-time comprehensive value is selected from the S intermediate sending channel combinations as the final sending channel, thereby obtaining S final sending channels.

[0062] The method of respectively predicting the S final transmission channels to obtain the corresponding second success rate includes: The S final sending channels are sequentially input into the pre-built second prediction model to obtain a corresponding second success rate.

[0063] Example 3 This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the big data analysis method for the success rate of SMS sending in multiple regions of Internet of Vehicles provided by the above methods is implemented.

[0064] Since the electronic device introduced in this embodiment is the electronic device used to implement the big data analysis method for the success rate of text messages sent in multiple-region Internet of Vehicles in the embodiment of this application, based on the big data analysis method for the success rate of text messages sent in multiple-region Internet of Vehicles introduced in the embodiment of this application, technical personnel in this field can understand the specific implementation methods of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application will not be introduced in detail here. As long as technical personnel in this field implement the electronic device used by the big data analysis method for the success rate of text messages sent in multiple-region Internet of Vehicles in the embodiment of this application, it belongs to the scope of protection of this application.

[0065] Example 4 The present embodiment discloses a computer-readable storage medium having a computer program stored thereon. When the computer program is executed, the big data analysis method for the success rate of SMS sending in multiple regions of Internet of Vehicles is implemented.

[0066] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0067] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0068] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0069] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0070] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0071] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0072] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0073] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0074] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A big data analysis method for the success rate of SMS sending in multi-region Internet of Vehicles, characterized in that: include: Obtain user-related information and current status information corresponding to the user to be sent, and determine the corresponding service provider based on the user-related information; Obtain M third-party platforms corresponding to the service provider, construct M initial sending channels based on the M third-party platforms and current state information, and perform predictions based on the M initial sending channels to obtain corresponding first success rates; According to the first success rate, M initial sending channels are screened to obtain N intermediate sending channels, the N intermediate sending channels are clustered to obtain S final sending channels, the S final sending channels are predicted separately to obtain corresponding second success rates, and the final sending channel corresponding to the largest second success rate is used as the target sending channel, where N≤M.

2. The big data analysis method for the success rate of SMS sending in multi-region Internet of Vehicles according to claim 1 is characterized in that: The method for determining the corresponding service provider based on user related information includes: Based on the information of the area where they are located, Q initial suppliers are determined, and the corresponding communication service level is determined according to the information of the vehicles to which they belong. Based on the communication service level, P intermediate suppliers are screened out from the Q initial suppliers, and the historical communication success rates corresponding to the P intermediate suppliers are calculated according to the historical communication records. The intermediate supplier corresponding to the maximum historical communication success rate is selected as the service provider.

3. The big data analysis method for the success rate of SMS sending in multi-regional Internet of Vehicles according to claim 2 is characterized in that: The method for constructing M initial sending channels based on M third-party platforms and current status information includes: Traverse M third-party platforms in turn, take the third-party platform, current time zone and current device as nodes, and take the current load information as the edge between nodes, so as to build a sending channel graph, and use the sending channel graph as the initial sending channel.

4. The big data analysis method for the success rate of SMS sending in multi-region Internet of Vehicles according to claim 3 is characterized in that: The method of performing predictions based on the M initial transmission channels to obtain the corresponding first success rate includes: Inputting the M initial sending channels into a pre-built first prediction model in sequence to obtain a corresponding first success rate; The construction method of the first prediction model includes: Acquire a sample data set, wherein the sample data set includes a historical initial sending channel and a historical first success rate; Divide the sample data set into a sample training set and a sample test set, and build a regression network; The historical initial transmission channel in the sample training set is used as input data of the regression network, and the historical first success rate in the sample training set is used as output data of the regression network, and the regression network is trained to obtain an initial regression network for predicting the first success rate; The initial regression network is tested using a sample test set, and the initial regression network with an output smaller than a preset error value is used as the first prediction model.

5. The big data analysis method for the success rate of SMS sending in multi-region Internet of Vehicles according to claim 1 is characterized in that: The method of screening the M initial sending channels according to the first success rate to obtain N intermediate sending channels includes: Traverse M initial sending channels, obtain the load stability data and area coverage data corresponding to the initial sending channels, calculate the load stability value according to the load stability data, calculate the area coverage value according to the area coverage data, determine the real-time comprehensive value based on the first success rate, the load stability value and the area coverage value, eliminate the initial sending channels whose real-time comprehensive values ​​are less than the preset comprehensive threshold, so as to obtain N intermediate sending channels.

6. The big data analysis method for the success rate of SMS sending in multi-region Internet of Vehicles according to claim 5 is characterized in that: The load stability data includes an average response delay, a bandwidth usage value, and a maximum fluctuation amplitude. The method for calculating the load stability value according to the load stability data includes: LSV= ; Where LSV is the load stability value, is the average response delay, is the bandwidth usage value, is the maximum fluctuation range, is the hyperbolic cosine function, is the hyperbolic sine function, is a logarithmic function with base e, is an exponential function with base e, , are all weight factors.

7. The big data analysis method for the success rate of SMS sending in multi-region Internet of Vehicles according to claim 5 is characterized in that: The area coverage data includes an area coverage ratio, a supporting equipment ratio, and a specific compliance value. The method for calculating the area coverage value according to the area coverage data includes: RCV= ; Where RCV is the regional coverage value, is the area coverage ratio, To support the equipment ratio, For a specific matching value, is the inverse cotangent function, , are all constants greater than 0.

8. The big data analysis method for the success rate of SMS sending in multi-region Internet of Vehicles according to claim 5 is characterized in that: The method of clustering N intermediate sending channels to obtain S final sending channels includes: According to the first success rate, load stability value and area coverage value, N intermediate sending channels are clustered to obtain S intermediate sending channel combinations, and the intermediate sending channel with the largest real-time comprehensive value is selected from the S intermediate sending channel combinations as the final sending channel, thereby obtaining S final sending channels.

9. A big data analysis platform for the success rate of SMS sending in multiple regions of vehicle networking, which is used to implement the big data analysis method for the success rate of SMS sending in multiple regions of vehicle networking as described in any one of claims 1 to 8, characterized in that: include: The first processing module is used to obtain user-related information and current status information corresponding to the user to be sent, and determine the corresponding service provider based on the user-related information; The second processing module is used to obtain M third-party platforms corresponding to the service provider, construct M initial sending channels based on the M third-party platforms and current state information, and perform predictions based on the M initial sending channels to obtain corresponding first success rates; Channel selection module: used to screen M initial sending channels according to the first success rate to obtain N intermediate sending channels, cluster the N intermediate sending channels to obtain S final sending channels, predict the S final sending channels separately to obtain the corresponding second success rate, and use the final sending channel corresponding to the largest second success rate as the target sending channel, wherein N≤M.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the big data analysis method for the success rate of text message sending in multiple regions of Internet of Vehicles as described in any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed, implements the big data analysis method for the success rate of SMS sending in multiple regions of Internet of Vehicles as described in any one of claims 1 to 8.

Images