An algorithm application method based on device model

Abstract

The present invention relates to the technical field of Internet of Things, and in particular to an algorithm application method based on a device model. The method comprises: receiving a request for an algorithm device storing a target algorithm to access the Internet of Things; performing data interaction with the algorithm device through the Internet of Things, and the Internet of Things obtaining a software model of the target algorithm; obtaining an interaction result; inputting the same input value into the software model of the target algorithm in the Internet of Things and the algorithm device for calculation for multiple times to obtain a first output result and a second output result; judging whether the algorithm device can be reliably accessed according to the interaction result and the first output result and the second output result; if the algorithm device can be reliably accessed, then agreeing to the request for the algorithm device to access the Internet of Things, and controlling the algorithm device to access the Internet of Things. The present invention can effectively reduce the cumbersome and complex problems of the Internet system through calculation, and can directly use and link structured data, thereby realizing rapid application conversion of the algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to an algorithm application method based on a device model. Background Art

[0002] The Internet of Things, or "Internet of Everything", is an extension and expansion of the Internet. It combines various information sensing devices with the Internet to form a huge network, which enables the interconnection of people, machines and objects at any time and any place. The existing Internet of Things technology is mainly used in smart home products, with routers as the core and mobile phones as the control terminals, to achieve intelligent control of various home products (such as refrigerators, air conditioners, lights, curtains), which greatly facilitates people's daily life. Of course, the Internet of Things technology also has certain applications in the fields of intelligent transportation, public safety, etc.

[0003] In the actual application of the Internet of Things, when a new algorithm needs to be loaded, the algorithm cannot be loaded as a separate application. Instead, the programmer needs to write the software model of the algorithm into the Internet of Things control system (hereinafter referred to as the Internet of Things system) in the cloud-based Internet of Things control system. In this way, when multiple algorithms need to be loaded, the cloud-based Internet of Things system will be too cumbersome, especially for tens of millions of users. Perhaps some users will not use the software models corresponding to certain Internet of Things terminals, but due to the use of other users, the Internet of Things system used by the user will also be cumbersome and complicated, which makes the Internet of Things system occupy a large volume, slow in processing speed, and makes the intervention of specific algorithms complicated.

[0004] In order to solve this problem, we propose an algorithm application method based on a device model of the present invention. Summary of the invention

[0005] The purpose of the present invention is to provide an algorithm application method based on a device model, which is used to solve the problems of the existing algorithm application mode causing the Internet of Things system to be cumbersome and complicated, the algorithm intervention to be complex, and the processing speed to be slow.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] An algorithm application method based on a device model, comprising:

[0008] Receive a request for an algorithm device storing a target algorithm to access the Internet of Things;

[0009] Performing data interaction with the algorithm device through the Internet of Things, so that the Internet of Things obtains a software model of the target algorithm;

[0010] Obtaining the interaction result of data interaction between the Internet of Things and the algorithm device;

[0011] Inputting the same input value into the software model of the target algorithm and the algorithm device in the Internet of Things for multiple times to perform calculations, and obtaining first output results of the software model of the target algorithm and second output results of the algorithm device corresponding to the multiple input values ​​respectively;

[0012] Determining whether the algorithm device can be reliably accessed according to the interaction result and the first output result and the second output result;

[0013] If the algorithm device can be reliably accessed, the request of the algorithm device to access the Internet of Things is approved, and the algorithm device is controlled to access the Internet of Things.

[0014] Furthermore, the controlling the algorithm device to access the Internet of Things further includes:

[0015] The software model of the target algorithm stored in the Internet of Things is deleted, and in a subsequent process, the input value input into the Internet of Things is directly calculated by the algorithm device.

[0016] Furthermore, if the algorithm device cannot be reliably accessed, the request for the algorithm device to access the Internet of Things is rejected, and an alarm is sounded to remind the staff that the algorithm device currently requested to access is unreliable.

[0017] Furthermore, data is exchanged between the Internet of Things and the algorithm device so that the Internet of Things obtains a software model of the target algorithm, including:

[0018] Sending algorithm query information to the algorithm device through the Internet of Things;

[0019] The Internet of Things receives the return data returned by the algorithm device in response to the algorithm query information within a preset time period starting from the initial moment; wherein the initial moment is the moment when the Internet of Things sends the algorithm query information to the algorithm device;

[0020] The Internet of Things generates a software model of the target algorithm according to the returned data using the following first formula:

[0021]

[0022] Among them, M ascii A software model representing a target algorithm, which is stored in the Internet of Things in ASCII form; D 16 Indicates the return data returned by the algorithm device in response to the algorithm query information of the Internet of Things, and its data format is hexadecimal format. If the Internet of Things does not receive the return data within the preset time from the initial moment, D 16 =0; A16 Indicates the data frame header in the preset hexadecimal format; E 16 Indicates the end of the data frame in preset hexadecimal format; len() indicates the number of data bits of the hexadecimal data in brackets; Indicates circular left shift; >> indicates right shift; ASCII{} means converting the data in the brackets into ASCII code data format; "error" indicates error in string format.

[0023] Further, the obtaining of the interaction result of the data interaction between the Internet of Things and the algorithm device includes:

[0024] The determination value of whether the interaction between the Internet of Things and the algorithm device is normal is obtained by the following second formula:

[0025]

[0026] Wherein, H represents the judgment value of whether the interaction between the Internet of Things and the algorithm device is normal; D 16 [1→len(A 16 )] represents data D 16 From 1st to len(A 16 ) bit data segment; D 16 {[N-len(E 16 )+1]→N} represents data D 16 From the Nth to the lenth (A 16 ) bit; N represents data D 16 The total number of data bits in ; Indicates a fully valid function. If all the equations in the brackets are valid, the function value is 1. If one or more of the equations in the brackets are not valid, the function value is 0. Indicates the existence of a function. If one or more of the equations in the brackets are true, the function value is 1. If none of the equations in the brackets are true, the function value is 0.

[0027] Further, after obtaining the determination value of whether the interaction between the Internet of Things and the algorithm device is normal through the second formula, it also includes:

[0028] Determine whether the determination value of whether the interaction between the Internet of Things and the algorithm device is normal is equal to 1;

[0029] If yes, continue to execute the step of inputting the same input value into the software model of the target algorithm in the Internet of Things and the algorithm device for calculation;

[0030] Otherwise, an alarm will alert the staff that the current interaction between the Internet of Things and the algorithm device is abnormal.

[0031] Further, judging whether the algorithm device can be reliably accessed according to the interaction result and the first output result and the second output result includes:

[0032] Calculate the control value of reliable access of the algorithm device by a third formula;

[0033] Determine whether the control value of the reliable access of the algorithm device is equal to 1, if so, determine that the algorithm device can be reliably accessed, otherwise determine that the algorithm device cannot be reliably accessed;

[0034] The third formula is:

[0035]

[0036] Wherein, G represents the control value of reliable access of the algorithm device; and represents the logical relationship and; || represents obtaining the absolute value; K represents the total number of times the same input value is input into the software model of the target algorithm in the Internet of Things and the algorithm device for calculation; It represents the first output result obtained by inputting the same input value into the software model of the target algorithm for the ath time; S0(a) represents the second output result obtained by inputting the same input value into the algorithm device for the ath time; a=1,2,…,K.

[0037] The present invention has at least the following beneficial effects:

[0038] The present invention directly connects the algorithm's software model to the Internet of Things through algorithm devices, thereby effectively reducing the cumbersome and complex problems of the Internet system. By implementing corresponding algorithm calculations in the algorithm device of the user's terminal, structured data can be directly used and linked, achieving rapid application conversion of the algorithm and greatly improving the speed of the algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0040] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention 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 invention and are not intended to limit the present invention.

[0042] Example 1

[0043] Please refer to the following for details Figure 1 , the present invention discloses an algorithm application method based on a device model.

[0044] Specifically, the method of the present invention comprises the following steps:

[0045] S1. Receive a request from an algorithm device storing a target algorithm to access the Internet of Things;

[0046] In this step, it is necessary to first clarify that the algorithm device includes but is not limited to: tangible devices such as USB flash drives and hard disks, and may also be integrated into a storage element of a certain product.

[0047] The target algorithm is stored in the algorithm device, and then connected to the Internet of Things via wired or wireless means.

[0048] S2. Interacting data with the algorithm device through the Internet of Things so that the Internet of Things obtains a software model of the target algorithm;

[0049] S3. Obtaining the interactive results of data interaction between the Internet of Things and the algorithm device;

[0050] S4. Input the same input value multiple times into the software model of the target algorithm in the Internet of Things and the algorithm device for calculation, and obtain the first output result of the software model of the target algorithm and the second output result of the algorithm device corresponding to the multiple input values;

[0051] S5. Determine whether the algorithm device can be reliably accessed based on the interaction result and the first output result and the second output result;

[0052] If the algorithm device can be reliably accessed, the request of the algorithm device to access the Internet of Things is approved, and the algorithm device is controlled to access the Internet of Things.

[0053] If the algorithm device cannot be reliably accessed, the request for the algorithm device to access the Internet of Things will be rejected, and an alarm will be sounded to remind the staff that the algorithm device currently requested to access is unreliable.

[0054] Specifically, the algorithm device is controlled to access the Internet of Things, that is, the algorithm device is directly connected to the Internet of Things, and calculations are performed directly through the algorithm device, thereby reducing the computing burden of the Internet of Things, and at the same time, the algorithm model can be quickly applied and converted in the Internet of Things.

[0055] Of course, in order to avoid the cumbersomeness of the Internet of Things system, the software model of the target algorithm stored in the Internet of Things should also be deleted, and the input values ​​input into the Internet of Things should be calculated directly through the algorithm device in the subsequent process.

[0056] Embodiment 2:

[0057] The method for obtaining the software model of the target algorithm for the specific Internet of Things in this embodiment specifically includes:

[0058] S21. Sending algorithm query information to the algorithm device through the Internet of Things;

[0059] S22. The Internet of Things receives the return data returned by the algorithm device in response to the algorithm query information within a preset time period starting from the initial moment; wherein the initial moment is the moment when the Internet of Things sends the algorithm query information to the algorithm device;

[0060] S23. The Internet of Things generates a software model of the target algorithm according to the returned data using the following first formula:

[0061]

[0062] Among them, M ascii A software model representing a target algorithm, which is stored in the Internet of Things in ASCII form; D 16 Indicates the return data returned by the algorithm device in response to the algorithm query information of the Internet of Things, and its data format is hexadecimal format. If the Internet of Things does not receive the return data within the preset time from the initial moment, D 16 =0; A 16 Indicates the data frame header in the preset hexadecimal format; E 16 Indicates the end of the data frame in preset hexadecimal format; len() indicates the number of data bits of the hexadecimal data in brackets; Indicates circular left shift; >> indicates right shift; ASCII{} means converting the data in the brackets into ASCII code data format; "error" indicates error in string format.

[0063] Embodiment 3:

[0064] This embodiment is used to specifically disclose the method for obtaining the interaction result of the data interaction between the Internet of Things and the algorithm device described in S3 in the embodiment 1, including:

[0065] S31. Obtain the determination value of whether the interaction between the Internet of Things and the algorithm device is normal by the following second formula:

[0066]

[0067] Wherein, H represents the judgment value of whether the interaction between the Internet of Things and the algorithm device is normal; D 16 [1→len(A 16 )] represents data D 16 From 1st to len(A 16 ) bit data segment; D 16 {[N-len(E 16 )+1]→N} represents data D 16 From the Nth to the lenth (A 16 ) bit; N represents data D 16 The total number of data bits in ; Indicates a fully valid function. If all the equations in the brackets are valid, the function value is 1. If one or more of the equations in the brackets are not valid, the function value is 0. Indicates the existence of a function. If one or more of the equations in the brackets are true, the function value is 1. If none of the equations in the brackets are true, the function value is 0.

[0068] S32. After obtaining the determination value of whether the interaction between the Internet of Things and the algorithm device is normal through the second formula, determine whether the determination value of whether the interaction between the Internet of Things and the algorithm device is normal is equal to 1;

[0069] If yes, continue to execute S4, that is, continue to execute the step of inputting the same input value into the software model of the target algorithm in the Internet of Things and the algorithm device for calculation;

[0070] Otherwise, execute:

[0071] S33. The alarm reminds the staff that the current interaction between the Internet of Things and the algorithm device is abnormal.

[0072] Embodiment 4:

[0073] This embodiment is used to specifically disclose the method of judging whether the algorithm device can be reliably accessed according to the interaction result and the first output result and the second output result described in S5 in the embodiment 1, including:

[0074] S51. Calculate the control value of reliable access of the algorithm device by the third formula;

[0075] S52. Determine whether the control value of the algorithm device for reliable access is equal to 1. If so, determine that the algorithm device can be reliably accessed, otherwise determine that the algorithm device cannot be reliably accessed;

[0076] Wherein, the third formula is:

[0077]

[0078] Wherein, G represents the control value of reliable access of the algorithm device; and represents the logical relationship and; || represents obtaining the absolute value; K represents the total number of times the same input value is input into the software model of the target algorithm in the Internet of Things and the algorithm device for calculation; It represents the first output result obtained by inputting the same input value into the software model of the target algorithm for the ath time; S0(a) represents the second output result obtained by inputting the same input value into the algorithm device for the ath time; a=1,2,…,K.

[0079] Therefore, in combination with the above embodiments, it can be known that:

[0080] The present invention uses a first formula to obtain the result of interaction and the software model of the target algorithm according to the interaction between the Internet of Things and the algorithm device, thereby realizing intelligent self-verification by mutual verification of software and hardware, reflecting the intelligence of the system; then uses a second formula to judge whether the interaction between the Internet of Things and the algorithm device is normal according to the interaction result of data interaction between the Internet of Things and the algorithm device, thereby knowing whether the currently connected algorithm device is connected normally, ensuring the reliability of the hardware; finally, uses a third formula to control whether the algorithm device needs to be reliably connected according to whether the interaction between the Internet of Things and the algorithm device is normal and the output results of the software models of the algorithm device and the target algorithm, thereby knowing whether the algorithm calculation of the currently connected algorithm device is normal, ensuring the accuracy of the algorithm inside the algorithm device.

[0081] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. An algorithm application method based on device model, It is characterized in that include: Receive a request for an algorithm device storing a target algorithm to access the Internet of Things; Performing data interaction with the algorithm device through the Internet of Things, so that the Internet of Things obtains a software model of the target algorithm; Obtaining the interaction result of data interaction between the Internet of Things and the algorithm device; Inputting the same input value into the software model of the target algorithm and the algorithm device in the Internet of Things for multiple times for calculation, and obtaining the first output results of the software model of the target algorithm and the second output results of the algorithm device corresponding to the multiple input values ​​respectively; Determining whether the algorithm device can be reliably accessed according to the interaction result and the first output result and the second output result; If the algorithm device can be reliably accessed, the request of the algorithm device to access the Internet of Things is approved, and the algorithm device is controlled to access the Internet of Things; The method of performing data interaction with the algorithm device through the Internet of Things so that the Internet of Things obtains the software model of the target algorithm includes: Sending algorithm query information to the algorithm device through the Internet of Things; The Internet of Things receives the return data returned by the algorithm device in response to the algorithm query information within a preset time period starting from the initial moment; wherein the initial moment is the moment when the Internet of Things sends the algorithm query information to the algorithm device; The Internet of Things generates a software model of the target algorithm according to the returned data using the following first formula: Among them, M ascii A software model representing a target algorithm, which is stored in the Internet of Things in ASCII form; D 16 Indicates the return data returned by the algorithm device in response to the algorithm query information of the Internet of Things, and its data format is hexadecimal format. If the Internet of Things does not receive the return data within the preset time from the initial moment, D 16 =0; A 16 Indicates the data frame header in the preset hexadecimal format; E 16 Indicates the end of the data frame in preset hexadecimal format; len() indicates the number of data bits of the hexadecimal data in brackets; Indicates circular left shift; >> indicates right shift; ASCII{} means converting the data in the brackets into ASCII code data format; "error" indicates error in string format.

2. The algorithm application method based on the device model according to claim 1, It is characterized in that The controlling the algorithm device to access the Internet of Things also includes: The software model of the target algorithm stored in the Internet of Things is deleted, and in a subsequent process, the input value input into the Internet of Things is directly calculated by the algorithm device.

3. The algorithm application method based on the device model according to claim 1, It is characterized in that If the algorithm device cannot be reliably accessed, the request for the algorithm device to access the Internet of Things will be rejected, and an alarm will be sounded to remind the staff that the algorithm device currently requested to access is unreliable.

4. The device model-based algorithm application method according to claim 1, It is characterized in that The obtaining of the interaction result of the data interaction between the Internet of Things and the algorithm device includes: The determination value of whether the interaction between the Internet of Things and the algorithm device is normal is obtained by the following second formula: Wherein, H represents the judgment value of whether the interaction between the Internet of Things and the algorithm device is normal; D 16 [1→len(A 16 )] represents data D 16 From 1st to len(A 16 ) bit data segment; D 16 {[N-len(E 16 )+1]→N} represents data D 16 From the Nth to the lenth (A 16 ) bit; N represents data D 16 The total number of data bits in ; Indicates a fully valid function. If all the equations in the brackets are valid, the function value is 1. If one or more of the equations in the brackets are not valid, the function value is 0. Indicates the existence of a function. If one or more of the equations in the brackets are true, the function value is 1. If none of the equations in the brackets are true, the function value is 0.

5. The device model-based algorithm application method according to claim 4, It is characterized in that After obtaining the determination value of whether the interaction between the Internet of Things and the algorithm device is normal through the second formula, the method further includes: Determine whether the determination value of whether the interaction between the Internet of Things and the algorithm device is normal is equal to 1; If yes, continue to execute the step of inputting the same input value into the software model of the target algorithm in the Internet of Things and the algorithm device for calculation; Otherwise, an alarm will alert the staff that the current interaction between the Internet of Things and the algorithm device is abnormal.

6. The device model-based algorithm application method according to claim 4, It is characterized in that The determining, according to the interaction result and the first output result and the second output result, whether the algorithm device can be reliably accessed includes: Calculate the control value of reliable access of the algorithm device by a third formula; Determine whether the control value of the reliable access of the algorithm device is equal to 1, if so, determine that the algorithm device can be reliably accessed, otherwise determine that the algorithm device cannot be reliably accessed; The third formula is: Wherein, G represents the control value of reliable access of the algorithm device; and represents the logical relationship and; || represents obtaining the absolute value; K represents the total number of times the same input value is input into the software model of the target algorithm in the Internet of Things and the algorithm device for calculation; represents the first output result obtained by inputting the same input value into the software model of the target algorithm for the ath time for calculation; S 0 (a) represents the second output result obtained by inputting the same input value into the algorithm device for calculation for the ath time; a=1, 2,…, K.

Images