A storage computing integrated peer-to-peer computing system

Abstract

The application relates to a storage-computing integrated peer computing system, multiple node devices cooperatively compute, event discovery is realized, or further, corresponding to the discovered event, the node device connected with the execution device which needs to respond to the event, the result data obtained through computation is used for response execution; through the transmission and computation of the result data, the result data obtained through computation can represent the sensing state sensed by the multiple sensors connected with the node device, the self state of the node device, the device state of the multiple execution devices connected with the node device, through the computation of the result data and the connection relationship between the node devices, the non-medium storage of the sensing state sensed by the sensors connected with the node devices, the self state of the node devices and the device state of the execution devices connected with the node devices is completed, and in the process of completing the non-medium storage, the response processing of mass business logic is synchronously completed.

Description

Technical Field

[0001] This invention relates to the fields of network technology and data processing technology, and more specifically, to a peer-to-peer computing system that integrates storage and computing. Background Technology

[0002] The conventional understanding of data processing involves recording data with clear meaning using corresponding storage media for storage purposes. Examples include user identity information, product type, product quantity, sensor-collected perception data, and judgment or recognition results obtained based on that data. All of these possess clear meaning, including intermediate data during data processing, which can still be considered data with clear meaning, such as feature data extracted during identity recognition. This corresponding data is then recorded on the storage medium. For data with clear meaning recorded and stored using storage media, the data must be pre-calculated before storage. Furthermore, in existing conventional data processing technologies, the computing unit and storage medium are set up independently, each responsible for separate calculations and storage.

[0003] Data leaks can easily occur when storage media are stolen or decrypted, or when personnel or equipment managing the storage media are hijacked. Furthermore, the storage capacity of a storage medium is directly related to the size of the data content with clear meaning; the larger the data content, the fewer data items can be stored on the storage medium. This is especially true for complex raw data, algorithms, and process data that ultimately require calculation to obtain judgment or identification results, which significantly reduces the storage capacity and efficiency of the storage medium.

[0004] In existing technologies, encryption mechanisms are typically used to encrypt data in order to enhance data security. However, regardless of how the encryption mechanism works, it is only encrypting data content that has a clear meaning. In essence, it cannot change the clear meaning inherent in the data content itself. For example, the data corresponding to the number "1" will still be encrypted regardless of how it is encrypted, as it is a data that has the clear meaning of "1".

[0005] In other words, the data content described above, possessing a clear meaning, refers to data whose meaning can be understood solely by itself; and, provided the data can be reproduced or reused, regardless of the processing applied to the original data, the corresponding processing method can achieve data reproduction or reuse. However, if the processed data is defective and cannot be reproduced, then storing the data is meaningless; therefore, the data processing described above is not data destruction.

[0006] The computational stage, which acquires data with clear meaning, is not synchronous with the storage stage, nor can it be synchronous. That is, data with clear meaning must be calculated before it can be stored on a storage medium. Conversely, the process of reading from storage and the process of calculating data with clear meaning are not synchronous, nor can they be synchronous. Therefore, the data storage stage after computation is vulnerable to intrusion and data theft or tampering due to the asynchronicity of computation and storage. If data is tampered with, reading the tampered data will lead to corresponding problems based on the tampering. The asynchronicity between computation and storage also makes the computation, storage, and transmission links between computation and storage security weaknesses, highly susceptible to attacks. Furthermore, asynchronous computation and storage require searching and retrieving the necessary input data from storage for each computation; the ever-growing storage volume leads to an exponential decrease in computational efficiency.

[0007] The aforementioned shortcomings arise because existing technologies typically employ a computation-storage separation architecture. For example, they use independent computing units for identity verification or recognition, meaning recognition is performed in only one location or repeatedly in multiple locations. The recognition (computation) result is then asynchronously stored on other components (even on the same machine, the computing and storage components are managed relatively independently and operate asynchronously). Each recognition, if successful, yields a correct result; if it fails, it yields an incorrect result or a conclusion of failure. Regardless of success or failure, a meaningful result is obtained in one or more locations and stored as data. Furthermore, if a device performing single-point computation or single-point storage (meaning that the device or a few devices are responsible for storage, as opposed to storing information through all devices—for example, blockchain's distributed ledger is not single-point storage, while distributed cloud storage is) is hijacked, information leakage immediately occurs. If the processing logic is tampered with, a security incident can occur (in the computation-storage separation model, even if the computation part makes a correct judgment, the storage stage may still be tampered with, causing a security incident).

[0008] For example, methods for verifying or identifying a person's identity include: verifying the user's password or using biometrics at the location where identification is required. However, these methods have several drawbacks. First, they pose significant security risks. If a password is stolen or a face is replicated, whether identification is performed at one location or multiple locations, there is a risk of identity spoofing. This is because the architecture separates computing and storage, making collaboration between computing units costly and preventing simultaneous computation by a massive number of units. Second, they require users to actively output information, resulting in a poor user experience. Third, as a single-point computing device, the host processing the identification logic is vulnerable to hijacking by hackers, and information leakage and security risks after hijacking are unavoidable.

[0009] For example, the method for confirming or identifying the identity of a vehicle is feature recognition; however, the disadvantages are that the recognition results are prone to breakage, the data source is not entirely reliable, the requirements for recognition technology are high, but the recognition accuracy is low.

[0010] The Internet of Things (IoT) based on the traditional single-point architecture with separate computing and storage makes it difficult to achieve secure collaboration among massive computing nodes. The security capabilities of existing IoT technologies, if distributed across a vast number of IoT devices, will be extremely weak. As a result, a large number of IoT devices can be hijacked by hackers. While this may not affect the normal operation of the devices under normal circumstances, it is much easier for hackers to launch a DDoS attack using a massive number of IoT devices, thus paralyzing the target system.

[0011] Furthermore, the single-point recognition method, which separates computation and storage, requires high-speed recognition operations at each point, placing high demands on hardware. As the amount of data increases, the execution efficiency will also decrease.

[0012] Existing technologies for intelligent management at the city level, exemplified by the current City Brain, still adhere to the traditional single-point aggregation model of information technology, where computing and storage are separated. The existing City Brain consists of a centralized service platform and multiple stations with different functions and roles. These stations are connected non-peer-to-peer through a relatively fixed, hierarchical aggregation relationship. Each station sends the results of its events or raw data directly or indirectly to the service platform for processing and network-wide coordination, achieving the so-called intelligent management goal. However, in the technical solution of the City Brain, the functions of each station are still essentially single-point identification, single-point computing, and a computing and storage separation model. The coordination between stations is actually a centralized platform managing the overall operations using a single-point computing and computing and storage separation model.

[0013] In addition to the shortcomings of single-point identification, single-point calculation, and the separation of calculation and storage at each site, the overall technical solution of the City Brain also has the following deficiencies:

[0014] Weak resistance to attacks: including single points of vulnerability to attack, information stored separately from computing is easily stolen or tampered with (especially by internal employees' hacking or unauthorized use), and privacy data is easily leaked;

[0015] Data security and authenticity are difficult to guarantee: including data being easily tampered with, false information, misinformation, outdated information, high costs of discovery and correction, great difficulty in governance, difficulty in assigning responsibility for data problems, and difficulty in responding in a timely manner;

[0016] Data silos exist: data cannot be fully shared between departments and sites, sharing costs are high, and there are high cybersecurity risks and information leakage risks after sharing, which in turn restricts the maximization of information effectiveness. Summary of the Invention

[0017] The purpose of this invention is to overcome the shortcomings of existing technologies and provide a peer-to-peer computing system that integrates storage and computing. It utilizes result data that lacks a clear meaning, transmitting and computing it between node devices to obtain a clear meaning. This allows for non-media storage and non-media retrieval, achieving the effect of integrated storage and computing. The result data itself does not directly indicate a clear meaning; that is, the result data itself cannot be reproduced or interpreted by any means. Instead, it is obtained during the transmission and computation process, thus eliminating the need to form any data content with a clear meaning or to store it. This achieves non-media storage and non-media retrieval while simultaneously completing the computation, judgment, and execution of business logic. It fundamentally changes the traditional single-point security-sensitive nature of information systems, ensuring reliable data sources and computation processes, high execution efficiency, low hardware requirements, and high recognition accuracy. It achieves non-specific feature recognition of visitors without requiring specific feature identification or obtaining visitor identity information.

[0018] The technical solution of the present invention is as follows:

[0019] A peer-to-peer computing system integrating storage and computing includes multiple node devices. Each node device is equipped with a data processing model, and there is no hierarchy among the node devices. Each node device processes the collected raw data through the data processing model, calculates the result data, and selects other node devices to receive the result data according to preset rules or the data processing model. After receiving the result data, the selected other node devices use the result data as one of the collected raw data and use their data processing model to calculate the result data of the current node device. This process continues, with multiple node devices in the peer-to-peer computing system performing collaborative computing to discover events. Alternatively, for each discovered event, the execution device connected to the node device that needs to respond to the event performs a response based on the calculated result data. Simultaneously, the result data represents the sensing state perceived by the sensors connected to the node devices, the node device's own state, and the device state of the execution devices connected to the node devices. Through the calculation of the result data and the connection relationships between the node devices, the system completes non-media storage of the sensing state perceived by the sensors connected to each node device, the self-state of each node device, and the device state of the execution devices connected to each node device, and performs computing tasks.

[0020] Preferably, different node devices collect raw data at their respective times and / or in their respective spaces. If it is necessary to trace the behavior, attributes, state, or event of a target, the current node device takes the need for target tracing as one of the inputs, and adds it to the calculation of the current result data along with other preceding result data and the current raw data, and then sends it to other node devices. Similarly, based on the preceding result data and the current raw data received by the current node device, the relationship between the preceding state value represented by the behavior, attributes, state, or event of the target in the raw data collected by each preceding node device and the current state value represented by the current result data of the current node device is calculated, and non-media reading is completed through the calculation of the result data.

[0021] As a preferred approach, when there is an execution requirement, during the process of non-media storage or non-media retrieval, the node device takes the execution requirement as one of the inputs and calculates the result data; based on collaborative computing, it judges the business logic corresponding to the execution requirement and executes the business logic through the execution device connected to the node device.

[0022] The beneficial effects of this invention are as follows:

[0023] This invention describes a peer-to-peer computing system integrating storage and computing. Multiple node devices collaborate to discover events, or, further, corresponding to discovered events, the execution devices connected to the node devices that need to respond to the events execute responses based on the computationally obtained results. Through the transmission and computation of the results data, the computationally obtained results data can characterize the sensing states perceived by multiple sensors connected to the node devices, the node devices' own states, and the device states of the multiple execution devices connected to the node devices. Through the computation of the results data and the connection relationships between the node devices, non-media storage of the sensing states perceived by the sensors connected to each node device, the self-state of each node device, and the device states of the execution devices connected to each node device is completed. During the non-media storage process, the response processing of massive amounts of business logic is completed simultaneously. That is, the node devices do not store the original data (according to legal or management regulations, sensors can be configured to store data for traditional evidence preservation needs), nor do they perform point-based identification using the collected original data on a single node device.

[0024] This invention simulates the effects of "storage," "reading" from "storage," and subsequent operations based on the "read" data obtained in real-time by a peer-to-peer computing system and its transmission between node devices. In this invention, the peer-to-peer computing system does not actually store data with explicit meaning. Instead, when there is a need (including a "traceability" need (such as obtaining data with explicit meaning) or an execution need (such as operations based on obtained data with explicit meaning)), the system transmits and calculates the result data (representing the perceived state of each node device) between the node devices to obtain the result corresponding to the need. This achieves an effect similar to "reading" from "storage," simultaneously realizing the calculation, judgment, and execution results of massive amounts of business logic. The "result" corresponding to the "traceability" need is not obtained by generating data corresponding to the "result" and storing it through a medium, but rather by calculating according to the need, thus achieving the integration of storage and computation. When there is an execution requirement, in the process of implementing something similar to "reading" from "storage", the calculation, judgment and execution of the business logic corresponding to the execution requirement are completed simultaneously; and, in the process of implementing something similar to "reading" from "storage", there is no need to output the "result" corresponding to the data with clear meaning, that is, the process of implementing something similar to "reading" from "storage" is carried out seamlessly.

[0025] The computation described in this invention is a causal and continuous computation performed by a massive number of node devices with massive logic (the entire peer-to-peer computing system processes massive demands at the same time). Hackers’ intrusion, hijacking, or tampering with any node device will cause errors in the interaction computation between the intruded, hijacked, or tampered node device and other node devices, thereby discovering the abnormality of the node device, activating corresponding measures for repair, or replacing the faulty node device.

[0026] When it is necessary to trace the behavior, attributes, state, or event of a target, the current node device takes the target tracing requirement as one of the inputs, and adds it to the calculation of the current result data along with other preceding result data and current raw data, and then sends it to other node devices. Similarly, based on the preceding result data and current raw data received by the current node device, the calculation of the current result data yields the relationship between the preceding state values ​​represented in the raw data collected by each preceding node device and the current state values ​​represented in the current result data of the current node device. This achieves a "reverse reasoning" effect, and further achieves a similar "reading" of "storage" while simultaneously completing the calculation and judgment of business logic. Therefore, the "reading" is not about "results" that already exist and are stored using media, but rather about obtaining them through calculation based on requirements. Furthermore, the calculation process itself completes both "storage" and "reading," forming a unified process, rather than separate processes with a sequential relationship.

[0027] This invention can also drive the execution device connected to the current node device to respond while calculating the result data, complete the calculation and judgment of business logic, and realize the execution of business logic; furthermore, it will also simultaneously perform "non-media storage" of the execution result. Therefore, this invention can simultaneously realize the "traceability" requirement and the execution requirement through the transmission of result data. By only transmitting data and executing the corresponding execution device, it can achieve the "storage-read-calculation-execution-storage" effect of the existing single-point computing architecture with separated calculation and storage, which is equivalent to the existing technology, through only the calculation process.

[0028] In this invention, state values ​​are used to represent various types of perceived data for a target, simplifying the amount of information corresponding to the data being transmitted. The data is transmitted based on a peer-to-peer computing system. Within the coverage of the peer-to-peer computing system, the execution devices connected to the node devices can respond to the behavior, attributes, states, or events of multiple targets during the transmission of result data.

[0029] This invention also simplifies various types of perceived data (i.e., result data) of the target through multi-dimensional matrix transcoding to obtain corresponding state values. Furthermore, as the result data is transmitted, states are continuously superimposed and updated, ensuring that each output result data from any node device contains a sequence of events and detailed representations of various dimensions over a considerable period covered by the peer-to-peer computing system. When needed, the result data is calculated and transmitted from the receiving node device through a series of other node devices. One or more node devices, based on the preceding result data received by the current node device, perform business logic calculations and judgments as the result data is transmitted between node devices. Correspondingly, this drives the execution devices connected to the node devices to respond. The response actions or results of these execution devices simulate a "backward calculation" and perform subsequent operations based on the "results" obtained from this "backward calculation." In the process, the raw and intermediate data that existing technologies need to store are all converted into result data that is constantly being transmitted. The storage of data with clear meaning is also converted into a calculation action. As a result, there is no need to store the complete raw data of the corresponding target type perception data. There is no need to rely on a huge and slow database to record massive targets and complex spatiotemporal correlations, which greatly reduces data storage costs, greatly improves operating efficiency, and saves computing power.

[0030] The "storage" and "retrieval" described in this invention actually involve calculating the result data, which contains massive sets of past features, to perform business logic judgments. This achieves an effect similar to "recalling" (i.e., "reverse deduction") historical states. Unlike architectures that separate computation and storage to read records from historical moments, this invention does not require, and can exist, storage media to "store" data with clear meaning for "retrieval." The "recall" of events or information in this invention is the result of real-time computation. All "recall" results are obtained from calculations by massive numbers of node devices. The calculation results of these massive number of node devices at each unit of time are a common intermediate calculation, encompassing a high-dimensional hybrid calculation result that describes the historical state of the target.

[0031] When the storage capacity of the medium is limited, the technical solution of connection relationship and result data calculation provided by this invention is used to replace the traditional medium storage. Assuming a directed acyclic transmission mode, if any one of the 100,000 node devices initiates "non-medium storage" or "non-medium reading", it is at the level of 100,000 factorials, and its state value has 456,573 bits (i.e. 10,456,573 state values). When multiple node devices initiate, 10,456,573 changes are formed accordingly. Therefore, the capacity of a city-level infrastructure can be regarded as close to infinite (in fact, the node devices in the path can choose the preceding node device as the subsequent node device, which is a cyclic transmission mode, and a node device can transmit the result data to multiple node devices, so the expression sequence is infinite).

[0032] Because individual node devices do not store data with explicit meaning, and the results of "storage" or "reading" are obtained through real-time calculation, this invention cannot be intruded upon, hijacked, have information stolen, or tampered with unless all node devices are hijacked simultaneously. In city-level deployments, the number of node devices can reach hundreds of thousands or even hundreds of millions. Existing hacking methods cannot simultaneously intrude into all node devices. Therefore, this invention is immune to intrusion, hijacking, information theft, and tampering by existing hacking methods.

[0033] In the aforementioned peer-to-peer computing system, there is no master-slave relationship among all node devices, and no fixed connection relationship between node devices (i.e., no fixed path for transmitting result data). Node devices only receive the computation results from other node devices and send out their own computation result data. The discovery of events and / or the response of corresponding execution devices do not rely on the identification and control of a single node device, but are confirmed through collaborative computation by multiple node devices in the peer-to-peer computing system. Furthermore, this invention does not require explicitly obtaining and claiming to have discovered the behavior, attribute, state, or event of a target. It can omit the explicit intermediate process judgment for a certain behavior, attribute, state, or event of a target, and therefore there is no storage step for this information, allowing for a direct final response. Based on a peer-to-peer computing system, this invention does not rely on single-point identification. It transforms the traditionally separate computing and storage stages into an integrated computing and storage stage, distributing the computing functions throughout the entire peer-to-peer computing system. This reduces the hardware and software requirements of single-point computing, resulting in high execution efficiency and significantly improved resistance to attacks. The system maintains a relatively symmetrical information state among node devices, making it immune to illegal data tampering. Even if a single node device is physically compromised and its transmitted data is altered, peer-to-peer computing involves highly redundant and complex calculations and multi-dimensional verification. Therefore, the alteration of data transmitted by a single node device does not affect the peer-to-peer computing results of a massive number of nodes. Furthermore, it allows for rapid location of faulty and tampered node devices, ensuring the reliability of peer-to-peer computing results. This, in turn, resolves the conflict between data sharing and information security between departments.

[0034] The data transmitted between node devices is the result of information processing, not the information itself. Therefore, the raw data (i.e., perceived data) collected does not need to be stored. Node devices only receive the calculation results output by other node devices and send out their own calculation results. The amount of information contained in a single calculation result is insufficient to reconstruct any event or target information. A definite result can only be obtained by joint calculation of the calculation results on the entire peer-to-peer computing system, multi-dimensional data matrix elements, and physical space and facility correspondence. The collaborative calculation has less dependence on the information transmitted by a few node devices. There is no storage process for storing data with clear meaning. This can fundamentally change the nature of traditional information systems that are single-point security sensitive.

[0035] The non-specific feature recognition described in this invention can determine that each unique object to be identified (i.e., the visitor) is itself without requiring specific features or specific identity information. (When calculations are not performed with the purpose of uniquely identifying the visitor, the intermediate result of identifying its uniqueness will not appear). This invention enables visitor identification, identity verification, ownership calculation, or event monitoring using non-specific feature recognition. It not only achieves high accuracy but also precise location identification, without explicit intermediate calculation results. It transforms the traditional storage process into a calculation process and merges it with the calculation and judgment of business logic. In the merged calculation steps, there is no distinction between calculations used to achieve equivalent storage effects and calculations used to implement business logic judgments, making it immune to existing hacking methods such as eavesdropping, hijacking, and attacks. This invention can recognize identity and ownership relationships without relying on specific features, protecting privacy while solving long-standing urban problems related to transportation, education, medical convenience, epidemic prevention, public services, emergency response, community services, market behavior, safe production, and civilized behavior. Simultaneously, it ensures that unauthorized access to peer-to-peer computing systems is prevented by temporary identity impersonation.

[0036] The non-specific feature recognition achieved by this invention effectively prevents risks caused by the theft or counterfeiting of specific features, greatly enhancing security. The non-contact, passive method implemented in this invention performs seamless identification of the object being identified, significantly improving ease of execution (it directly calculates and drives the corresponding response action; in computations not aimed at outputting identity, there is no intermediate identity recognition process). Based on the aforementioned peer-to-peer computing system, this invention can be easily deployed over coverage areas of hundreds of meters or hundreds of kilometers, suitable for various geographical scales.

[0037] The present invention identifies targets (including visitors), confirms their identity and ownership, or monitors events. Since it does not transmit or store the original data, there is no risk of privacy information leakage; correspondingly, it can resolve the contradiction between public safety and privacy protection.

[0038] After the peer-to-peer computing system is deployed at the city level, node devices no longer perform single-point identification and information processing. Sensors can be connected to nearby node devices, and a sufficiently large number of node devices constitute a peer-to-peer computing system, which can effectively immunize against existing hacking intrusion methods. Simultaneously, due to its architectural characteristics, the peer-to-peer computing system eliminates communication channels that hackers can use, further immunizing against hijacking of IoT devices. With the widespread adoption of city-level peer-to-peer computing systems and their use to process all IoT sensing devices, the cost for hackers to launch DDoS attacks will become increasingly high, eliminating other attack channels. Furthermore, with numerous applications providing services to citizens, businesses, devices, and the government through node devices, hackers will no longer be able to launch DDoS attacks against critical applications. Detailed Implementation

[0039] The present invention will be further described in detail below with reference to the embodiments.

[0040] This invention addresses the security weaknesses caused by the single-point computation and separation of computation and storage in existing technologies, as well as the high storage overhead and vulnerability to data leakage associated with storing meaningful data through storage media. It provides an integrated storage and computation peer-to-peer computing system. Instead of simply storing meaningful data through storage media, it employs a real-time result data computation solution using "non-media storage" and "non-media retrieval," achieving a "reverse reasoning" effect to simulate the "reading" effect of "storage." Furthermore, it integrates "storage," "reading," and business logic calculations into a single computation process, executing business logic to achieve an effect equivalent to "reading" and "storing" and subsequent operations. This peer-to-peer computing system fundamentally changes the traditional single-point security sensitivity of information systems. It offers reliable data sources and computation processes, high execution efficiency, low hardware requirements, and high recognition accuracy. It achieves non-specific feature recognition of visitors without requiring specific feature identification or access to visitor identity information.

[0041] Regarding the definitions of "media storage" and "non-media storage" in this invention, specifically, "media storage" refers to storing data (or data content) with a definite meaning through a storage medium, while "non-media storage" refers to storing data (or data content) with a definite meaning without a storage medium. "Having a definite meaning" means that a definite meaning can be determined from the data, such as user identity information, product type, product quantity, sensor-collected perception data, judgment results or recognition results obtained based on perception data, etc.; that is, the meaning corresponding to the data itself can be determined solely by the data itself, and the content that the data itself expresses can be known. Furthermore, "media storage" and "non-media storage" are not actually custom antonyms, but rather indicate a fundamental difference in technical solutions, representing completely different technical means based on entirely different technical principles. The "non-media storage" described in this invention does not mean that no storage medium is used at all during implementation, nor that any data is stored using any storage medium. Rather, in the technical features corresponding to the effects of "storage" and "reading," data content with a clear meaning (or representing a clear result) is no longer directly stored. That is, it is not recorded on the storage medium, but the original data is not directly stored, and no simple single-point calculation is performed on the original data in advance. For example, for the number "1," the data corresponding to the number "1" is no longer recorded on the storage medium directly or after encryption. When "reading" is required, the action to be performed after "reading" the number "1" is actually directly responded to through real-time calculation. This achieves the effect of completing a "reading"-like operation within the calculation step (in the calculation step, there is no distinction between which part of the calculation step is equivalent to "reading" or equivalent to "storage") and performing subsequent operations based on the "storage" of the "reading."

[0042] After obtaining data with clear meaning by "reading" from "storage," there are usually subsequent operations, which are executed by execution devices with specific functions. These operations include outputting the "storage" that was "read," controlling the execution device based on the "storage" that was "read," and the execution device responding to and executing the "storage" that was "read," and so on. For example, displaying data with clear meaning is actually done by displaying the data with clear meaning through a display device (which is an execution device whose specific function is display). For example, controlling a projector device through a user's actions is actually done by recognizing the user's actions, obtaining corresponding control commands, and using the control commands to control the projector to perform corresponding operations. For example, controlling the opening of an access control system based on a visitor's access request and identity information is actually done by the access control system acting as an execution device, responding to the visitor's access request based on the visitor's identity information.

[0043] It is evident that the execution of business logic can infer the inevitable existence of a "reverse reasoning" effect, thus confirming that the present invention necessarily involves calculations of "non-media storage" and "non-media reading" (not necessarily output). In this invention, the "non-media storage" and "non-media reading" of "non-media storage" are forms of intermediate state data. The existence of the corresponding intermediate state data constitutes the "non-media storage" described in this invention. Obtaining a result with a clear meaning through calculation using the intermediate state data constitutes the "non-media reading" described in this invention. When subsequent operations are required based on the "storage" of "reading," the calculation, judgment, and execution of business logic typically only allow the user to perceive or know the execution result. However, "non-media storage" and "non-media reading" may not be perceived by the user, or do not need to be perceived by the user, or there may not even be an independent "storage" and "reading" process of "reading." Furthermore, by transmitting the result data, this invention can simultaneously achieve the original data, logical judgment, and execution requirements needed for "traceability". It can achieve the "storage-reading-computation-execution-storage" effect of the existing single-point computing architecture with separate computation and storage by simply transmitting data and executing the corresponding execution device.

[0044] In the integrated storage and computing peer-to-peer computing system of the present invention, multiple node devices are set up. Each node device is equipped with a data processing model. Each node device processes the collected raw data through the data processing model, calculates the result data, and selects other node devices to receive the result data according to preset rules or the data processing model. After receiving the result data, the selected other node devices use the result data as one of the collected raw data and use their data processing model to calculate the result data of the current node device.

[0045] In the peer-to-peer computing system described above, there is no hierarchy among the node devices; due to this lack of hierarchy, a decentralized network and computing architecture are formed. Unlike traditional information-based single-point aggregation and computing-storage separation computing models, the data transmission direction between node devices in this invention does not have a fixed, preset path relationship. In the peer-to-peer computing system described above, each node device senses all targets within its sensing area; for a given node device, the collected raw data is processed to obtain result data, which is then propagated to other node devices; other node devices that receive the result data use it as one of the collected raw data, thus influencing the result data of other node devices. For ease of explanation, the aforementioned "a certain node device" will be referred to as the "current node device" and the "other node devices" will be referred to as the "subsequent node devices". One of the effects is that the result data obtained by the subsequent node devices is not entirely determined by the original data they collect, but is jointly determined by the result data output by the current node device. In particular, the result data output by the current node device may change the data processing model and parameters used by the subsequent node devices to calculate the result data, thereby affecting the result data of the subsequent node devices. For example, if the output data of the current node device is related to the raw data collected by subsequent node devices, it is necessary to consider the impact of the output data of the current node device on the accuracy of the output data of the subsequent node devices. Specifically, for the perception of a specific target, if the result data is calculated based solely on the raw data collected by subsequent node devices, it can only reflect the real-time (including real-time location and time) single-point result judgment of the target within the perception range of the subsequent node devices. However, the output data of the current node device reflects the direct perception data and result judgment of the target at other locations and at other times, or other indirectly related perception data and result judgments, which helps to improve the accuracy and comprehensiveness of the result data of the subsequent node devices, including superimposed calculations of the same dimension and correlation references of different dimensions.

[0046] Because there is no master-slave relationship between nodes in a peer-to-peer computing system, point-to-point transmission is possible. Therefore, for a given calculation result corresponding to a specific perceived data point of a target, as reflected in the output data of one node, the information is relatively symmetrical among the other nodes that receive that result data. Other nodes use the received result data as input, combining it with their own sensor data to calculate their own result data. Their own result data naturally encompasses both the received result data and the information from their own sensors, and is then transmitted to the next layer of nodes. Thus, for a specific perceived data point of a target, information is relatively symmetrical across all nodes. This system is immune to the impact of tampering and forgery on the computation process and results of individual node devices, thus preventing the data from being affected. It also serves as a means to detect faulty, tampered, or non-compliant node devices, fundamentally solving the inherent vulnerabilities of traditional information technology. These vulnerabilities stem from information asymmetry, leading to false, forged, and erroneous information, which can become entry points for fraud and cyberattacks. Furthermore, it addresses the problems of poor accuracy, excessive processing time, low credibility, and poor responsiveness in complex applications. It also reduces security weaknesses arising from the independent operation of storage, retrieval, and computation, ultimately making it a true information infrastructure for urban integrated management and the digital economy. Unlike blockchain technology, which still relies on independent computation by each node to produce deterministic results and emphasizes original data storage, this invention focuses on peer-to-peer collaborative computation between node devices. Through this collaborative computation, each node device can adjust the computation, structure, and parameters of its own data processing model. This adjustment is a feedback mechanism from all node devices, transforming the computation of all node devices into a unified whole. Instead of individual nodes performing computation independently, all node devices collaboratively complete the calculation. Once the data processing model of the node device is adjusted, this adjustment will have an impact on the next data processing iteration.

[0047] In this implementation, a given node device can selectively send its result data to specific other node devices, depending on the implementation requirements. In practice, the result data of a particular node device does not necessarily need to be received by all other node devices; some node devices can be selected as the next layer of subsequent node devices to receive it.

[0048] In this invention, node devices in a peer-to-peer computing system collect any perceptible data (i.e., raw data) within their sensing range using all the sensors they are equipped with. Simultaneously, each node device also receives result data output from other node devices, calculates its own result data, and outputs it. Thus, the entire peer-to-peer computing system continuously senses, collects, inputs, outputs, and calculates data. Based on this, result data propagates among the node devices in the peer-to-peer computing system. Based on this result data, multiple node devices perform collaborative calculations to discover events. Alternatively, corresponding to a discovered event, the execution device connected to the node device that needs to respond to the event executes a response based on the calculated result data. In this invention, result data propagates and is calculated among the node devices in the peer-to-peer computing system, and the execution device connected to the node device responds to one or more combinations of the behavior, attributes, states, or events of one or more targets.

[0049] If the execution device connected to the node device needs to obtain basic data outside the peer-to-peer computing system to determine the response to one or more combinations of behaviors, attributes, states, or events of one or more targets, the node device connected to the peer-to-peer computing system with accessibility data acquisition conditions (including one or more combinations of system departments, operation locations, authorized personnel identities, triggering conditions, time, and collected values ​​corresponding to the response, all serving as the basis of a multidimensional matrix, which is a measure of these basic elements) performs basic data acquisition. The accessibility data is then used as input to the node device for calculation to obtain the current result data. Based on this, the present invention can solve effects that existing technologies cannot achieve. For example, existing methods stipulate that if a hospital receives more than 10 food poisoning cases, it is considered an emergency event and needs to be reported. Without specific aggregation, if 5 hospitals receive a total of 10 food poisoning cases from the same school, an emergency response will not be triggered. However, the present invention, based on the peer-to-peer computing system, can detect if 5 hospitals have received a total of 10 food poisoning cases from the same school, thereby triggering an emergency response.

[0050] In this invention, the resulting data itself does not directly show, represent, or express a definite meaning; that is, the resulting data itself is not processed by other means to reproduce or interpret a definite meaning. In fact, during the implementation of this invention, the resulting data represents an intermediate, high-dimensional, mixed computational result encompassing the historical state description of the target. During transmission, there is no transformation, conversion, compilation, or encryption of the original data or data with definite meaning for the purpose of transmission. To obtain a result with definite meaning, such as confirmation of an event or information, this invention obtains it during the transmission and computation of the resulting data, thus requiring no data content with definite meaning to be formed, let alone stored. The "non-media storage" and "non-media reading" of "non-media storage" described in this invention are defined in this way, thus revealing the definition of "computation-storage integration."

[0051] Specifically, the method for transmitting result data between node devices is as follows: the current node device receives the previous result data output by the preceding node device, and calculates the current result data by combining it with the current raw data collected by the current node device, and transmits it to the subsequent node device; and so on, transmitting the result data between node devices. The result data represents the sensing state perceived by the sensors connected to the node device, the state of the node device itself, and the state of the execution device connected to the node device. Through the calculation of the result data and the connection relationship between node devices, the non-media storage of the sensing state perceived by the sensors connected to each node device, the state of each node device itself, and the state of the execution device connected to each node device is completed, and massive computing tasks are performed.

[0052] The "storage" and "retrieval" described in this invention actually involve calculating the result data, which contains a massive set of past features, to achieve an effect similar to "recalling" (i.e., "reverse deduction") historical states. This differs from single-point calculations that retrieve records from historical moments. Therefore, it does not require, and can exist, a storage medium to "store" data with clear meaning for "retrieval." The "recall" of events or information in this invention is the result of real-time calculation. All "recall" results are obtained from calculations by a massive number of node devices. The calculation results of these node devices at each unit of time are a common intermediate calculation, encompassing a high-dimensional, mixed calculation result that describes the historical state of the target. The business logic calculations, judgments, and executions based on events or information confirmed by "recall" in this invention are also the result of real-time calculations, manifested in the corresponding execution of events or information by the execution device.

[0053] In this invention, the result data transmitted between node devices can be result data covering multiple targets (i.e., result data), specifically a comprehensive state of one or more combinations of the behaviors, attributes, states, or events of multiple targets. In this invention, sensors connected to the node devices are used to sense their coverage area to obtain full-volume sensing data corresponding to the current time and current location within their coverage area (which necessarily includes the behaviors, attributes, states, or events of multiple targets). Specifically, some or all node devices are equipped with at least one type of sensor to collect corresponding different types of sensing data and calculate the current result data. For any node device where a target is sensed, the current node device receives the preceding result data output by the preceding node device, combines it with the current raw data collected by the current node device, calculates the current result data, and transmits it to the subsequent node device; this process continues to complete the transmission of result data between node devices. In other words, in each transmission of result data by a node device, the received data is combined with the current raw data it has collected, and calculations are performed based on the data processing model to obtain result data. Then, the result data is sent to other node devices in the next layer (in most cases, this includes multiple subsequent node devices, each of which corresponds to multiple current node devices, and each node device corresponds to multiple preceding node devices; the logical principle is the same throughout the network). That is, a node device completes one transmission of result data.

[0054] In practice, different node devices may collect different types of sensor data due to the different sensor types they are configured with. Consequently, the types of sensing data collected by different node devices may also be different. Therefore, if the current node device does not have one or more types of sensors configured by the preceding node device, the current node device will still use the preceding result data containing the corresponding type of sensing data sent by the preceding node device as input and process it synchronously with the sensing data collected by the current node device's sensors to avoid the loss of some types of sensing data during the transmission of result data, which would affect the integrity of the result data.

[0055] In this invention, the current raw data represents all the data output by the sensors connected to the current node device, including the current state of the current behavior, attributes, status, or events of multiple targets within its coverage area (i.e., the perception state sensed by the sensors connected to the node device, the node device's own state, and the device state of the execution device connected to the node device can correspond to the state of the target's behavior, attributes, status, or events; or, when the target is an object sensed by the sensors, or a node device or an execution device connected to the node device, then the perception state sensed by the sensors connected to the node device, the node device's own state, and the device state of the execution device connected to the node device include the state of the target's behavior, attributes, status, or events). The preceding result data represents all the data output by the sensors connected to the preceding node devices, including the preceding comprehensive state of the target's preceding behavior, attributes, status, or events. The current result data represents all the data output by the sensors connected to the current node device and the result data received from other node devices, including the current comprehensive state of the target's current behavior, attributes, status, or events. The current comprehensive state is a combination of the current state and the preceding comprehensive state. For example, in a simple single-dimensional, single-target scenario, the preceding node device outputs the preceding result data as ab (i.e., the result data output by the previous-level node device is a, the perceived data of the preceding node device is b, and the combined current result data is ab), and the current node device's current raw data is c, then the current result data is abc. The same logic applies to other complex multi-dimensional, multi-target scenarios.

[0056] In this invention, the order of connected node devices in each transmission of result data is not necessarily fixed. That is, for a given node device, the preceding and following node devices in the previous transmission of result data are not necessarily the preceding and following node devices in the next transmission. For example, in a peer-to-peer computing system, three node devices x, y, and z may transmit result data x to node y and y to node z in one transmission of result data; however, in another transmission, the three node devices x, y, and z may not have a data transmission relationship. The same applies to all node devices in the network. Correspondingly, the transmission path in a single transmission of result data does not mean that the node devices constituting the transmission path are on the same transmission path in every transmission of result data. The transmission path is obtained by summarizing the result data transmissions that have occurred, rather than a pre-planned path (including fixed and dynamic paths) or a calculated path. The transmission path in this invention only represents a summarizing result and does not imply its existence. Therefore, in this invention, for a given node device, after each calculation to obtain result data, other node devices are reselected to receive the result data according to preset rules or a data processing model. Thus, the node devices in the peer-to-peer computing system have a dynamic connection relationship, without fixed connections. After the current node device receives the result data from the preceding node device, the connection between the current node device and the preceding node device is terminated, and the current node device waits to be selected to receive result data from one or more other node devices, forming a dynamic connection relationship. In this embodiment, the data processing model of the current node device selects the subsequent node device to receive the current result data. For example, when the peer-to-peer computing system "observes" a scene, group A node devices transmit result data to group B node devices. The result data sent by group B node devices to group C node devices will contain a combination of various details of the scene. According to a preset or data processing model, the execution devices connected to these node devices will also perform corresponding actions, thereby completing the calculation from the "observation" of the scene to the responses from each node device, execution device, and personnel.

[0057] This invention, by being able to operate independently of a specific transmission path, distinguishes itself from existing technologies that rely on a specific path to determine events (a specific path is typically a description of a single target, usually required for single-point identification in event determination). It achieves event determination or response through a different technical approach. The response includes the response from the execution device connected to the node device. In this embodiment, the node device is equipped with one or more output modes, including hardware / software interface output, screen output, indicator light signals, and electromagnetic wave signals. Each output module is implemented as a corresponding execution device.

[0058] In this invention, when using dynamically connected node devices to achieve "non-media storage" and "non-media retrieval," it is similar to human memory, which is based on the connections between neurons. The shrinking of connections between neurons does not mean the disappearance of memory; when a stimulus is received and the connection is re-established, the corresponding memory will be recalled. In this invention, data transfer between node devices is similar to the connection relationships upon which neurons form and reproduce memories. Therefore, data transfer between node devices in the peer-to-peer computing system described in this invention achieves both "storage" and "computation."

[0059] Specifically, taking a given node device as the current node device, and considering the data transmission between its preceding and subsequent node devices (in this invention, preceding and subsequent node devices are only used to describe their sequential relationship with the current node device in the current calculation and data transmission process, and do not imply a necessary sequential or priority relationship between them), the current node device receives the result data output by other node devices (including preceding node devices), and subsequent node devices receive the result data output by other node devices (including the current node device). For the current node device, the collected sensing data is combined with the result data from other node devices (including preceding node devices) to calculate the result data of the current node device, and this result data is sent to other node devices (including subsequent node devices). Similarly, the working process of subsequent node devices is the same as that of the current node device, and preceding node devices also receive the result data from the preceding node devices of their preceding nodes and perform the same working process as the current node device; that is, the node devices in the peer-to-peer computing system perform the same working process. Furthermore, the node devices in the peer-to-peer computing system perform collaborative calculations as sensing data is collected and result data is calculated. In this process, the output data of a certain node device is only received and used as input by the subsequent layer of node devices, and the output data of the subsequent layer of node devices will cover the output data of the preceding layer of node devices (including the aforementioned node device).

[0060] In peer-to-peer computing systems, all events are processed synchronously, without necessarily requiring explicit output of specific events or their details. In such systems, only sensor perception and corresponding execution device responses are explicitly defined; all other intermediate processes are handled simultaneously through collaborative computing. This means that the intermediate process of event discovery is seamless during the operation of this invention; as collaborative computing progresses and node devices acquire their results, the corresponding execution devices automatically respond and execute. Furthermore, this invention differs from the single-objective calculations of existing technologies by simultaneously calculating multiple objectives, such as toll fees. While existing single-objective calculations calculate the specific cost for a particular vehicle's route, this invention can use 5000 node devices to calculate the fees for all 35000 vehicles out of 50000. This is equivalent to simultaneously calculating the routes, matching toll conditions, and calculating fees for all 50000 vehicles, directly driving the corresponding terminals (i.e., the execution device is a payment terminal) to perform seamless payment deductions or displaying a toll QR code based on the vehicle's location (i.e., the execution device is a display terminal). During this period, the above objectives and logic are calculated simultaneously, and there is no calculation mode for a certain node to determine the path information, toll standard, location judgment, and terminal interactive control of a certain vehicle.

[0061] Different node devices collect raw data at their respective times and / or in their respective spaces. If it is necessary to trace the behavior, attributes, state, or event of a target, the current node device takes the need for target tracing as one of the inputs, and adds it to the calculation of the current result data along with other preceding result data and the current raw data, and then sends it to other node devices. Similarly, based on the preceding result data and the current raw data received by the current node device, the relationship between the preceding state values ​​represented by the target's behavior, attributes, state, or event in the raw data collected by the preceding node devices and the current state values ​​represented by the current result data of the current node device is calculated, thus completing "non-media reading" through the calculation of the result data. In practical implementation, preceding node devices may not be able to discover or determine the target's behavior, attributes, state, or events. However, the raw data collected by preceding node devices that cover the target inevitably includes sensor perception data of the target. After obtaining the relationship between the preceding state values ​​representing the target's behavior, attributes, state, or events in the raw data collected by each preceding node device and the current state values ​​representing the current result data in the current node device, a "backward deduction" effect can be achieved based on the relationship between the result data that can discover or determine the target's behavior, attributes, state, or events, through the calculation of subsequent result data and the response of the execution device. In fact, the so-called "backward deduction," "recall," and "tracing" in this invention are all similar effects, which are actually obtaining new calculation results, i.e., new result data. Based on the technical solution of this invention, it is known that the required result is obtained through the calculation of result data, and the final effect is exactly similar to the traditional understanding of "backward deduction," "recall," and "tracing." Traditional understanding of "reverse engineering," "recalling," and "tracing" historical data recorded through storage media involves actually performing a data search operation. The "reverse engineering," "recalling," and "tracing" achieved by this invention involves the current node device calculating the result data to generate current result data corresponding to the "original data collected by previous node devices regarding the target's behavior, attributes, state, or events" that have existed or occurred in the past. This drives the execution device connected to the current node device to respond, and the execution device performs the corresponding action.Specifically, for example, node a (the current node device) determines the perception state of the target by node m (the preceding node device) at a past time by adding a specific description to the result data calculated by node a. This description is converted into a state value in the output matrix (i.e., the expression form of the result data). Then, the result data calculated by node a is transmitted to node m or sent to other node devices, participating in the calculations of other node devices one by one until it finally reaches node m. Node m, using the same principle, adds a corresponding description to the result data calculated by node a. This description is converted into a state value in the output matrix. Similarly, the execution device of the node device corresponding to the "tracing" requirement, such as node z1, z2, etc., outputs a response, which can be a response action or a response result. This response action or response result is the result corresponding to the "tracing" requirement. When the result is obtained, it is considered that a "reverse reasoning" effect has been completed. Therefore, the "non-media reading" described in this invention is actually based on "non-media storage," utilizing the results of "non-media storage" for acquisition.

[0062] This invention simulates the effects of "storage," "reading" from "storage," and subsequent operations based on the "read" from "storage," based on the real-time computation results obtained by a peer-to-peer computing system and the transmission of these results between node devices. Furthermore, the simulation of "storage," "reading," and business logic judgments is indistinguishable, all based on the transmission of results data. In this invention, when an execution requirement exists, the node device takes the required execution requirement as one of its inputs and performs calculations on the results data. Based on collaborative computing, it judges the business logic corresponding to the execution requirement and executes the business logic through the execution device connected to the node device. Since the peer-to-peer computing system does not actually store data with explicit meaning, but rather, when there is a requirement (including a "traceability" requirement (such as obtaining data with explicit meaning) or an execution requirement (such as operations based on obtained data with explicit meaning)), it transmits and calculates results (representing the perceived state of each node device) between node devices to obtain results corresponding to the requirement. This achieves an effect similar to "reading" from "storage" and performing business logic judgments, or realizes the results of business logic calculations, judgments, and executions. In this context, the acquisition of the "result" corresponding to the "traceability" requirement is not achieved by generating data corresponding to the "result" and storing it through a medium, but rather by performing calculations based on the requirement, thus achieving the integration of storage and computation. When there is an execution requirement, the calculation, judgment, and execution of the business logic corresponding to the execution requirement are completed simultaneously during the process of implementing something similar to "reading" from "storage." Furthermore, the process of implementing something similar to "reading" from "storage" does not require outputting a "result" corresponding to data with a clear meaning; that is, the process of implementing something similar to "reading" from "storage" is carried out seamlessly.

[0063] In this invention, the "reverse reasoning" effect is not necessarily the work of a single node device. In most cases, it's the overall result achieved by multiple node devices through connections and the transmission of result data. When a result not stored in media is needed, an extraction command (including a need for target tracing) is issued to the node devices. The node device receiving the extraction command processes the data (i.e., a type of raw data) related to the person, device, and scenario that issued the command, similar to raw data collected by sensors. The calculated result data is then sent to other node devices. Through collaborative computation among the node devices, one or more appropriate node devices are driven to respond. The data processing models of each node device can, in terms of structure and training, encompass permission judgments based on real identity, scenario, and complex rules.

[0064] As the result data of this invention is transmitted, its state is continuously superimposed and updated. Thus, each output result data from any node device contains an event sequence and details across various dimensions covered by the peer-to-peer computing system over a considerable period. When needed, from the node device receiving the request, through a series of node devices, calculations and transmissions are performed. One or more node devices, based on the preceding result data received by the current node device, drive the execution device connected to the node device to respond through collaborative computation, achieving an effect similar to "backward calculation" (in most cases, exhaustive enumeration is not required; instead, result data that meets the conditions is output by the corresponding node device. The effect of collaborative computation by multiple node devices is to filter out suitable result data and output it on the node device that meets the conditions. This filtering is not from all explicit data, but rather an output during the process of multiple node devices calculating and transmitting comprehensive calculation result data covering massive events). Furthermore, the result data is a simplified state value. After receiving the result data in state value form, the node device can directly perform combined calculations without first performing a "backward calculation" to obtain the target's past historical state. In practice, a "backward calculation" is explicitly performed and output only when the traceability of the target's behavior, attributes, state, or event is required—that is, when business logic needs to be executed—and the target cannot be achieved based on simplified state values. (In this invention, "non-media storage" actually achieves a similar "backward calculation" effect through computation. The calculation of the result data is improved through the multi-dimensional matrix provided by this invention, which is one of the effects of the current node device performing the current result data calculation.) Especially in peer-to-peer computing systems, the result data is often not returned to the initiating point. The purpose of initiating traceability is to determine what purpose needs to be achieved based on the traceability result. For example, it may be necessary to give the traceability result that meets the conditions to a specific party, i.e., to "backward calculate" the node device that meets the traceability result. This requirement to provide the traceability result will be added to its own result data, which will then drive the terminal devices connected to it or the terminal devices of several other node devices to output the result.

[0065] This invention differs from traditional methods in that what is actually transmitted between node devices (including between node devices in peer-to-peer computing systems) is a state representation (such as a representation through state values), not the state data itself. In this invention, the state representation can be a simplified transcoding, which can discard and compress some original information while achieving the accuracy of the event target, or it can be simplified transcoding in the original accuracy manner, thereby enabling communication between node devices with very small bytes, but ensuring that a massive number of node devices can accurately calculate and obtain the behavior, attributes, states, or events of massive targets when needed (wherein, the acquisition is often unnecessary).

[0066] For example, in a simplified embodiment, target a is sensed sequentially by node devices 1, 2, and 3, all the way to node device 9. The target sensing data output by node device 2 to node device 3 is target a from node device 1 to node device 2, i.e., 1-2, which can be described by a single state value in a matrix. Subsequently, node device 3 also senses target a, and its sensing result is added in a matrix, i.e., 1-2-3, and sent to the target node device. 1-2-3 is still a state value in the matrix. Similarly, the target sensing data transmitted by node device 9 to the next group of node devices is target a from node device 1 to node device 9, i.e., node device 1-2-3-4-5-6-7-8-9, which is also still just a single state value in the matrix. In practice, an intermediate judgment result for target 'a' is not typically generated. Instead, node device 1 processes its sensor perception along with the result data received from preceding node devices to obtain a matrix-form expression value (containing state values ​​representing the category perception data of target 'a'), and then passes it to node device 2. Similarly, node device 2 calculates the result data, processes it to obtain a matrix-form expression value (containing state values ​​representing the category perception data of target 'a'), and then passes it to node device 3. This process encompasses the transmission path of node devices 1-2-3-4-5-6-7-8-9 (perceiving target 'a'), and also covers various other perceptible details, as well as multiple states and characteristics of other targets.

[0067] In a full coverage scenario, the path information involved in the node devices is often multi-dimensional. Correspondingly, the node devices will receive multiple result data. For example, node device x may receive tracking sequences of target a from node devices corresponding to paths 123, 825, abc, dbm, lmn, etc. Node device x will aggregate these result data into a matrix for expression. Therefore, although these node devices cover target a from their own different paths, at the convergence point of all paths, node device x, the result data of all node devices for target a will be expressed in matrix form at the position of node device x. The expression result is still a state value.

[0068] Although this invention does not require determining the target's behavior, attributes, state, or events by generating a path, the result data output by each node device reflects the preceding result data, that is, the preceding behavior, attributes, state, or events of the target are integrated into the preceding state. Therefore, based on the preceding result data received by the current node device and the current raw data perceived by itself, calculations are performed to drive the execution device connected to the current node device to respond, thus achieving an effect similar to that obtained by "reverse calculation". For example, when it is necessary to find the location of target 'a' 15 minutes ago, the node device receiving the search request adds the search request to its current result data calculation and transmission. Then, the result data calculated by the node device will likely include node devices that previously sensed target 'a', until all node devices that sensed target 'a' 15 minutes ago have corresponding representations in their result data. After transmission by several node devices, the node device suitable for outputting to the requester outputs the result data that meets the requirements. Furthermore, the node device does not need to store the original data about target 'a'. That is, based on this invention, it is not necessary to identify the original data to find target 'a', but rather to first obtain the location of target 'a' 15 minutes ago through a process similar to "backtracking", and then feed it back to the requester through the execution device on some node devices.

[0069] In this invention, the resulting data is a simplified transcoding format of a multidimensional matrix. Specifically, it involves: simplifying and transcoding different types of perception data belonging to different targets collected by different sensors on the node device according to transcoding rules to obtain matching perception codes; constructing a perception multidimensional matrix using the perception codes corresponding to all current raw data collected by the node device; and combining the perception multidimensional matrix with the preceding result data in multidimensional matrix form to calculate the current result data in multidimensional matrix form, representing the current comprehensive state of the target's current behavior, attributes, and status. The preceding result data in multidimensional matrix form is also implemented using the method of "simplifying and transcoding different types of perception data belonging to different targets collected by different sensors on the node device according to transcoding rules to obtain matching perception codes; and constructing a perception multidimensional matrix using the perception codes corresponding to all current raw data collected by the node device."

[0070] In specific implementation, the multidimensional matrix obtained by the node device, which contains the target's behavior, attributes, state, and events, is simplified and transcoded. This simplification is then repeated. Furthermore, to further simplify the complex original data and facilitate the transcoding of the multidimensional matrix, this embodiment exhaustively enumerates all perceptual abbreviations and the perceptual multidimensional matrices they form, assigning a specific abbreviation value to each perceptual multidimensional matrix. An M-bit N-ary sequence is constructed, with each bit of the N-ary sequence assigned one of K different symbols. Each specific value of the M-bit N-ary sequence is matched one-to-one with each abbreviation value; where the value of M×N is greater than the number of abbreviation values. In practical implementation, once the peer-to-peer computing system is built, parameters such as the location, time, sensor type, and quantity of node devices can be clearly defined, both at the time of construction and during later maintenance and updates. Therefore, enumerating all perceptual codes and their corresponding multidimensional perceptual matrices is quite simple, and the data volume is not large. For example, if there are 100 million possibilities, 10,000 different symbols can be used to construct a base-10,000 sequence, i.e., a 2-digit base-10,000 sequence, such as X1X0. X1 and X0 can each be assigned one of the 10,000 different symbols, resulting in a total of 100 million values ​​for X1X0, each corresponding to one of the 100 million possibilities. If a larger amount of information is required during implementation, the number of digits in the base-10,000 sequence can be increased according to implementation needs, such as X3X2X1X0, which has a total of 10... 16 Each value corresponds to one out of a quadrillion possibilities. The matrix identifier sequence can be distributed and encrypted using non-volatile storage on various node devices, expressed through machine learning models, or represented through chip circuit structures.

[0071] In this embodiment, one implementation of the transcoding rule is as follows: different types of sensing data belonging to different targets collected by different sensors set on the node device are predefined into several levels, and all levels are divided into several level segments; a corresponding level segment identifier is assigned to each level segment, and a predefined type identifier is assigned to each type of sensing data. The type identifier + level segment identifier constitutes the original code parameter; the difference between the level of the sent type of sensing data and the first value of its corresponding level segment is set as a correction value.

[0072] Multiple sets of original code parameters that need to be sent simultaneously are arranged into an original code parameter string, and the correction values ​​are arranged into a correction value string. The original code parameter string is converted into a matching abbreviated code value, and the correction value string is converted into a matching correction code. The abbreviated code value + correction code is sent to the subsequent node device.

[0073] After receiving the abbreviated code value and the correction code, the subsequent node device translates the abbreviated code value back into the original code parameter string, and decomposes the original code parameter string into several original code parameters corresponding to the current node device; it translates the correction code back into the correction value string, and decomposes the correction value string into several correction values ​​corresponding to the current node device; it adds the correction values ​​to the first value of the level segment corresponding to the original code parameter to restore the level of the type of perception data sent by the current node device (in most cases, the subsequent node device will directly use the abbreviated code value + correction code as one of its own inputs for processing, without the need for translation and restoration).

[0074] The simplified transcoding approach described in this invention first simplifies the complex data before restoring it. In this invention, all original code parameter strings of the current node device are enumerated first, and a specific simplified code value is assigned to each original code parameter string. In subsequent node devices, the correspondence between the original code parameter strings and simplified code values ​​is the same as that of the current node device. Similarly, all correction value strings of the current node device are enumerated first, and a specific correction code is assigned to each correction value string. In subsequent node devices, the correspondence between the correction value strings and correction codes is the same as that of the current node device. Compared with existing technologies, only the most concise simplified code values ​​are transmitted during transmission, greatly saving bandwidth utilization. Without expansion, it can be used to transmit more complex and larger amounts of data. Especially for complex data with a large number of enumerated parameters, the method of segmenting and then correcting, compared to defining a parameter level for each level of parameter and then enumerating the original code parameters, avoids the deficiency of insufficient simplification of simplified code values ​​when the latter is applied to complex data with a large number of enumerated parameters.

[0075] To achieve the goal of simplifying the transmitted content, the word length of the abbreviated code value is less than the word length of the original code parameter string, and the word length of the correction code is less than the word length of the correction value string. In this invention, the number of bits in the abbreviated code value and the correction code is determined based on the number of exhaustively enumerated original code parameter strings and correction value strings, so that the number of original code parameter strings and correction value strings that match the abbreviated code value and the correction code is not less than the number of exhaustively enumerated original code parameter strings and correction value strings.

[0076] As an easy-to-implement implementation method, in this invention, if the number of exhaustively enumerated original code parameter strings and correction value strings is less than 256, then both the simplified code value and the correction code are represented using ASCII code, with each original code parameter string and correction value string matched with one ASCII code. One ASCII code consists of 8 binary number combinations, representing 256 possible characters. Each character can be used to represent one original code parameter string or one correction value string. One original code parameter string plus one correction value code represents a combination of multiple sets of parameters transmitted in parallel each time, based on a predetermined number of parameters.

[0077] Furthermore, if the number of exhaustively enumerated original code parameter strings and correction value strings is greater than the number of ASCII codes, then each original code parameter string and correction value string matches at least two ASCII code bits, and these multiple ASCII code bits are arranged to form an ASCII code string. Specifically, the ASCII code string includes a certain number of ASCII code bits, and the number of original code parameter strings and correction value strings matched by the ASCII code string... ,in, That is, in order to ensure that the number of possible characters included in the ASCII code string is greater than the number of exhaustive original code parameter strings and correction value strings, in practice, the number of bits in the ASCII code string is determined based on the number of exhaustive original code parameter strings and correction value strings, so that the number of original code parameter strings and correction value strings matched by the ASCII code string is not less than the number of exhaustive original code parameter strings and correction value strings.

[0078] The above embodiments using ASCII code are merely a convenient example for illustrating the present invention. The simplified code value and correction code described in this invention can also be other binary codes with a preset number of bits (such as 8 bits or 1 byte in ASCII code), and the code is formed based on the number of bits in the binary code. Count of characters.

[0079] For example, consider sending performance status parameters for three devices a, b, and c. The performance status of devices a, b, and c is collected. Each device has 30 levels of parameters, from 0 to 29. Exhaustively listing the original parameter strings yields 27,000 combinations. The acquired performance status data for the three devices is represented by 9 characters, such as a15b27c18. In computer storage and transmission, these 9 characters require 9 eight-bit binary codes, meaning a total of 9 bytes (72 bits) of information need to be transmitted.

[0080] In this embodiment, the parameters of each device are classified into six segments, such as a0-4, a5-9, a10-14, a15-19, a20-24, and a24-29. The same applies to devices b and c. A parameter segment identifier is generated based on which segment the parameter level to be sent falls into. This results in 216 possible combinations of parameter segments for the three devices, which can be represented using only one ASCII character. A parameter correction table is predefined in the current node device. The correction value represents the numerical increment of the parameter level within its corresponding segment, i.e., the difference between the parameter level and the first value of the segment. For example, the correction values ​​for a15b27c18 are 0, 3, and 3 respectively, so the correction value string is 033. The parameter correction table is an exhaustive combination of correction value strings. In this embodiment, there are 125 possible correction value strings, which can also be represented using one ASCII character. It can be seen that this invention can transmit 9 bytes of information using only two bytes. For example, the combination a15b27c18 corresponds to the character "p" in the transcoding mapping table and the character "k" in the parameter correction table. "pk" is transmitted to subsequent node devices. These subsequent node devices pre-set a transcoding mapping table and a parameter correction table with content completely identical to the current node device. The transcoding mapping table shows that "p" corresponds to the level segments a15-19, b24-29, and c15-19, while the parameter correction table shows that "k" corresponds to 0, 3, and 3. The correction value is added to the first value of the level segment to reconstruct a15b27c18.

[0081] Through the above process, 9 bytes of information can be transmitted using only 2 bytes, thus achieving the purpose of this invention.

[0082] Combining multidimensional matrix encoding, the above example can be evolved as follows: the xyz coordinates of the abnormal temperature point A that protrudes from the background observed by thermal camera 1 can be represented by abc (equivalent to recording data for the target in only three dimensions, and so on for multidimensional ones). After simplified transcoding, the data of A in the multidimensional matrix is ​​pk. In the multidimensional matrix output by the node device, the observation result of thermal camera 1 is Apkmw, the observation result of thermal camera 2 is Cabdef, and the data of other sensors are similar, ultimately forming a multidimensional matrix.

[0083] Based on the simplified transcoding described above, in specific implementation, according to implementation requirements, the result data obtained by the node device in the multidimensional matrix can be represented as the data of the multidimensional matrix, the state value of the multidimensional matrix data, or the result of simplified transcoding of the multidimensional nested matrix data.

[0084] Node devices perceive targets and obtain result data covering the target's behavior, attributes, state, or events. The result data obtained by each node device includes multiple target behaviors, attributes, states, or events with corresponding time and / or spatial parameters; time and / or space are used as dimensions in a multidimensional matrix. In this embodiment, relatively stable basic data such as the installation location, sensor type, surrounding facilities and environment, terrain, purpose, and attributes of each node device can actually serve as the basis for multidimensional matrix calculation. The multidimensional matrix outputs a label of these basic data, without needing to put these basic data into the multidimensional matrix; furthermore, the combinations of label values ​​are finite, and a transformation value can be output by combining them to participate in the calculation of result data by other node devices.

[0085] The node devices are equipped with at least one type of sensor to collect different corresponding types of sensing data. The sensors on the node devices perceive the target, and the perception time is used as one dimension of a multi-dimensional matrix. All node devices are synchronized in time to ensure consistency in perception time and minimize the impact of time errors on the accuracy of the resulting data. Alternatively, each type of data perceived by each type of sensor can be used as one dimension of the multi-dimensional matrix (depending on the sensor, some sensors can perceive multiple types of sensing data), or the types of sensors that meet correlation criteria can be combined as one dimension of the multi-dimensional matrix.

[0086] In this embodiment, the sensor includes one or more of the following: a camera, a vibration sensor, a lighting device, an electromagnetic device, and an elemental composition sensor.

[0087] In this invention, the current node device selectively sends its current result data to specific other node devices. The principle of selective sending is based on preset fixed rules, dynamic rules, or a model trained through machine learning to determine the specific other node devices. The model trained through machine learning is a reinforcement training model based on the node itself, using the previous result data of the node device as annotations for reinforcement training.

[0088] Based on the principle of selectivity, the node devices that need to transmit result data are added to the node list. Then, the result data calculated by the node device (i.e., after simplified transcoding) is sent to the node device selected from the list of communicably reachable nodes according to the principle of selective transmission.

[0089] In practical implementation, traditional single-point identification methods can be used to identify visitors at designated locations, achieving the purpose of identity verification and associating location information. Alternatively, the peer-to-peer computing system provided by this invention can be used for non-specific feature-based identity identification. The peer-to-peer computing system of this invention is based on collaborative computing, does not rely on single-point identification, and distributes computing functions across the entire network, reducing the hardware and software requirements of single-point computing, resulting in high execution efficiency and significantly improved anti-attack capabilities. The system maintains a relatively symmetrical information state among node devices, thus preventing illegal data tampering. Even if a single node device is physically compromised and its transmitted data is tampered with, the tampering of data transmitted by a single node device does not affect the overall network computing results because the network-wide computing is a highly redundant and complex calculation with numerous multi-dimensional verifications. Furthermore, it can quickly locate the faulty and tampered node device, ensuring the credibility of the overall network computing results. Therefore, it can resolve the contradiction between data sharing and information security between departments.

[0090] The result data transmitted between node devices can be the processing result of information rather than the information itself. Therefore, the raw data collected (i.e., perceived data) does not need to be stored. Node devices only receive the calculation results output by other node devices and send out their own calculation results. The amount of information contained in a single calculation result is insufficient to reconstruct any event or target information. A definite result can only be obtained by joint calculation of the calculation results on the entire peer-to-peer computing system, multi-dimensional data matrix elements, and physical space and facility correspondence. The collaborative calculation has less dependence on the information transmitted by a few node devices, which can fundamentally change the nature of traditional information technology's single-point security sensitivity.

[0091] In this invention, the visitor's identity information can be obtained through collaborative computing using the peer-to-peer computing system provided by this invention. Specifically, this invention utilizes the peer-to-peer computing system to perform non-specific feature recognition and / or location recognition on visitors. The term "non-specific feature recognition" differs from the common understanding of "recognition" in a strict conceptual definition. Commonly, "recognition" refers to determining the concrete or specific identity information of a target (in this invention, the target may include the aforementioned perceived target and the visitor, both of which can be simultaneously perceived and identified using the peer-to-peer computing system), such as who they are (including their name and specific information indicating their identity) or what they are (e.g., a car, a person). However, the "recognition" in this invention's "non-specific feature recognition" refers to identifying each unique visitor as themselves; that is, for a given object to be identified, its existence is unique. After implementing "non-specific feature recognition," this invention determines that the object to be identified (i.e., the visitor who has not been identified or had their identity confirmed) is itself, and not another object to be identified. The result of "non-specific feature recognition" does not require determining the specific characteristics of the object to be identified, nor does it require determining the object's identity information or concrete form. For example, if a person is considered object A to be verified, and an object is considered object B to be verified, then after implementing "non-specific feature recognition," it is not necessary to identify whether object A is a person or what their specific identity is, nor is it necessary to identify whether object B is an object or what kind of object it is; rather, it is necessary to determine that object A is object A itself, and object B is object B itself. Then, corresponding services or controls can be provided for object A or object B.

[0092] The node devices are equipped with data acquisition devices (in specific implementations, these may include one or more of the following: image acquisition devices, audio acquisition devices, temperature measurement devices, vibration frequency sensing devices, lidar, chemical sensors, and electromagnetic induction devices) and a computing module. The data acquisition devices include at least one type of sensor for collecting sensing data of different corresponding types. The computing module calculates the resulting data based on a data processing model. Node devices located at different acquisition positions (i.e., at different physical installation locations) collect at least one point sample from the visitor; the point sample is sensing data corresponding to the sensor type. Based on this, without needing to obtain the visitor's identity information, multiple node devices in the peer-to-peer computing system perform collaborative computation to determine that each unique visitor is themselves, achieving non-specific feature recognition; furthermore, it can further realize visitor location recognition.

[0093] Specifically, taking a given node device as the current node device, and considering the data transmission between its preceding and subsequent node devices (in this invention, preceding and subsequent node devices are only used to describe their sequential relationship with the current node device in the current calculation and data transmission process, and do not imply a necessary sequential or priority relationship between them), the current node device receives the result data output by other node devices (including preceding node devices), and subsequent node devices receive the result data output by other node devices (including the current node device). For the current node device, the collected sensing data is combined with the result data from other node devices (including preceding node devices) to calculate the result data of the current node device, and this result data is sent to other node devices (including subsequent node devices). Similarly, the working process of subsequent node devices is the same as that of the current node device, and preceding node devices also receive the result data from the preceding node devices of their preceding nodes and perform the same working process as the current node device; that is, the node devices in the peer-to-peer computing system perform the same working process. Furthermore, the node devices in the peer-to-peer computing system perform collaborative calculations as sensing data is collected and result data is calculated. In this process, the output data of a certain node device is only received and used as input by the subsequent layer of node devices, and the output data of the subsequent layer of node devices will cover the output data of the preceding layer of node devices (including the aforementioned node device).

[0094] In peer-to-peer computing systems, all events are processed synchronously, and it is not necessary to explicitly produce staged results such as what event was discovered or what the specific content of the event is. In peer-to-peer computing systems, only the sensor's perception and the corresponding execution device's response are explicit. All other intermediate processes are processed simultaneously through collaborative computing. That is, during the operation of this invention, the intermediate process of event discovery is imperceptible. As collaborative computing proceeds and the node device obtains the result data, the corresponding execution device automatically responds and executes.

[0095] To further ensure the trustworthiness of the data source and computation process, in this invention, all node devices encrypt their computational results based on an encrypted consensus mechanism, obtaining encrypted results, which are then sent to other node devices. The encrypted consensus mechanism includes one or more consensus mechanisms, with different mechanisms corresponding to changes in the encryption algorithm structure and parameters of the node devices.

[0096] Node devices communicate using standard-sized data packets (i.e., result data or calculation results). In this invention, the node devices of the peer-to-peer computing system are similar to human neurons. Just as each neuron does not transmit specific data directly describing external events, the node devices do not output raw data. Instead, they process the raw data acquired by connected sensors and data acquisition devices into standard-sized data packets (i.e., result data or calculation results, similar to nerve impulses in neurons) based on their own data processing models (similar to the biological characteristics of nerve cells). The information contained in a single data packet is insufficient to reconstruct any event or target information. A definite result can only be obtained through collaborative computation involving the calculation results across the entire peer-to-peer computing system, multi-dimensional data matrix elements, and the correspondence between physical space and facilities. Collaborative computation has little dependence on the data output by a few node devices, and it simultaneously processes all requests received or initiated by all node devices. It is a collaborative verification computation of highly multi-dimensional related information, thus fundamentally changing the traditional single-point security sensitivity of information systems.

[0097] To ensure data integrity and the effective execution of collaborative computing, the peer-to-peer computing system in this invention deploys a QoS mechanism, which prioritizes ensuring the transmission quality of result data between node devices.

[0098] In practical implementation, the peer-to-peer computing system can be networked using one or a combination of 4G, 5G, or MESH modes to suit different application scenarios. The optimal solution is achieved by considering factors such as feasibility and cost. The MESH mode is based on the LTE standard, communicating at the LTE physical layer. Data is carried by a customized frame structure, and interaction is performed using a dedicated wireless communication protocol. Customizing the frame structure to suit the computing needs of the peer-to-peer computing system and employing a proprietary wireless communication protocol developed for urban cluster peer-to-peer computing systems further enhances its security and reliability. Furthermore, the wireless algorithm is fully adapted to the multipath channel environment controlled by a consensus mechanism required for peer-to-peer computing systems. Communication distances range from 100 meters to 10 kilometers within cities, and up to 120 kilometers in the field using omnidirectional antennas. In this embodiment, the Mesh network communication distance is 50-150 meters between indoor nodes and 50 meters to 120 kilometers between outdoor nodes, with each node capable of simultaneously transmitting to 65,535 nodes. In addition, when networking in 4G and 5G modes, there is no limit to the communication distance, and the number of node devices that can be connected depends on the computing power of the computing chip and the communication latency.

[0099] In a peer-to-peer computing system, for a specific point sample of an object to be identified, the result data transmitted from the node device that collected the point sample to other node devices allows subsequent node devices to adjust their perceptual attention based on the features of that point sample (it is not necessary for the result data to contain the features of the point sample, but rather that the features of the point sample participate in the computation of the preceding node device, so that the result data of the preceding node device can be used as input to the data processing model of the subsequent node device, allowing the subsequent node device's data processing model to achieve the effect of adjusting perceptual attention during computation); or, the features of the point sample can be reported for subsequent node devices to adjust their perceptual attention (the features of the point sample are directly described in the result data). If other subsequent node devices do not detect the features of the point sample, but can determine from the features of other point samples that the undetected features of the point sample still belong to the object to be identified, then the features of the undetected point sample are continued to be described in the result data of the current node device and transmitted to other node devices. For example, if a preceding node device senses the color of an object A to be identified, but the current node device does not sense the color of the object A to be identified, but it can be determined from the sensing data of other node devices that there is another object A to be identified besides other objects to be identified, then the color of the object A to be identified that has not been sensed will still be represented in the result data of the current node device.

[0100] In this embodiment, the method for reporting the features of the point sample for subsequent node devices to adjust the perceptual attention is as follows: adjusting the parameters of the data processing model of the subsequent node device based on the features of the point sample provided by the preceding node device, so that the subsequent node device can improve the computing power of the point sample to identify its features; or, the subsequent node device uses the perceptual attention model to match the features of the received point sample to adjust the computing power.

[0101] The “feature” mentioned above has a different meaning from the “feature recognition” in the prior art. The “feature recognition” in the prior art usually refers to information that can determine the identity of the visitor, while the “feature” in this invention represents a kind of perceived data belonging to the object to be identified, such as coordinates, colors belonging to the object to be identified, etc. The “feature” perceived by a single point may not be able to directly complete the “non-specific feature recognition” of the object to be identified.

[0102] In this embodiment, the method for reporting the features of the point sample for subsequent node devices to adjust the perceptual attention is as follows: based on the result data expressing the features of the point sample provided by the preceding node device (in this invention, the features of the point sample are usually not provided themselves, but expressed in the result data), or the features of the point sample (i.e. the features of the point sample itself), the parameters of the data processing model of the subsequent node device are adjusted so that the subsequent node device can improve the computing power of the point sample to identify its features; or, the subsequent node device uses the perceptual attention model to match the features of the received point sample or the result data expressing the features of the point sample to adjust the computing power.

[0103] When a node device processes the output data from several preceding node devices, based on the data processing model, if the objects to be identified described by several preceding node devices can be determined to be the same target through certain common point sample features, the point sample features and other information described by each node device are merged into the same target. For example, point sample features in physical space that almost completely overlap at the same time can be determined to be the same target.

[0104] When the result data received by a node device indicates that the flag used by the current node device to identify the object to be identified before the current reception of result data is different from the flags used by other node devices to identify the object to be identified, and the flags assigned to the object by other node devices have been updated, then the flag used by the current node device to identify the object to be identified before the current reception of result data is converted. Specifically, the method for converting the flag used by the current node device to identify the object to be identified before the current reception of result data is as follows:

[0105] The flag used by the current node device to identify the object to be identified before the current reception of result data is replaced with the latest flag assigned to the object by other node devices; this is a simpler implementation of the present invention.

[0106] Alternatively, the conversion relationship between the flag used by the current node device to identify the object to be identified before the current reception of result data and the updated flag assigned to the object by other node devices can be recorded, and the conversion can be performed when the result data of the current node device received in the current reception needs to be referenced; this is a relatively complex implementation method provided by the present invention.

[0107] Alternatively, the node device can deploy a conversion model to perform corresponding conversions on the labels of multiple objects to be identified based on the input raw data or result data; this is a more complex implementation provided by the present invention.

[0108] In this invention, in order to improve the effectiveness of "non-specific feature recognition", for one or more point samples collected successively by node devices at different collection locations, if the feature values ​​of one or more point samples at different collection locations meet the preset similarity conditions or are determined by a specific model to have a correlation threshold, and are unique at each collection location, then it is determined that the point samples at different collection locations are correlated.

[0109] On the other hand, for one or more point samples collected simultaneously by node devices at different collection locations, if the node devices at different collection locations collect data on the same spatial field, and there is only one object to be identified in the spatial field, or the collected point sample can correctly point to one of the multiple objects to be identified, then for a certain object to be identified, one or more point samples collected by node devices at different collection locations are correlated.

[0110] In this invention, the data acquisition device of the node device includes one or more combinations of an image acquisition device, an electromagnetic induction device, a temperature measurement device, and a vibration frequency sensing device, and a lidar. The data acquired by the aforementioned devices (i.e., one or more combinations of the image acquisition device, electromagnetic induction device, temperature measurement device, and vibration frequency sensing device) and the three-dimensional point cloud acquired by the lidar, or the point cloud generated from images acquired by multiple image acquisition devices, are jointly calculated to obtain three-dimensional points with data. The image color, contour, lines, reflectivity, motion trend, electromagnetic characteristics, temperature, temperature change trend, vibration frequency, and vibration frequency change trend based on two-dimensional perception are used as additional attributes of the corresponding three-dimensional points to constitute an attributed three-dimensional point cloud. Combining electromagnetic induction, temperature patterns, vibration frequency change characteristics, motion correlation (different motion correlations exhibited by different materials such as ropes and fabrics), and reflectivity, the correspondence between each region of the attributed three-dimensional point cloud and each part or related part of the 3D appearance of the object to be identified is determined. This embodiment utilizes the attributes and correlations of attributed 3D point clouds to determine the relationships between points, the correspondence between the regions to which each related point belongs and each part or related part of the 3D appearance of the object to be identified, and can more accurately determine the point sample features belonging to the object to be identified, thereby improving the efficiency and accuracy of "non-specific feature recognition".

[0111] In the process of "non-specific feature recognition," this invention can, when necessary, also acquire the identity information of the object to be identified located outside the peer-to-peer computing system. Specifically, when it is determined that the identity information of the object to be identified (i.e., the visitor) located outside the peer-to-peer computing system needs to be acquired, an identity information acquisition command is triggered. This command is used as one of the inputs in the calculation of the result data of the node device. By driving the node device in the peer-to-peer computing system, which is connected to the barrier-free data collection conditions capable of obtaining the identity information of the object to be identified located outside the peer-to-peer computing system, to respond with the corresponding result data, the identity information of the object to be identified is acquired. The acquisition of identity information is also the result of collaborative computation; that is, the determination that identity information needs to be acquired triggers the acquisition of identity information, rather than being additionally triggered by a specific request command. Based on this invention, if permission calculation is triggered by a request command, in most cases, it can be completed without acquiring identity information. Only in a few cases, when it is found that permission calculation cannot be completed without acquiring identity information, will the determination that identity information needs to be acquired be generated according to implementation requirements. For example, if collaborative computing reveals that a person's identity information exists in several location-based QR code registration systems, package pickup registration systems, or consumer registration systems, and prior authorization from the person or legal access to these systems is obtained, then the peer-to-peer computing system can drive node devices connected to these systems via barrier-free data collection. The obtained information is then sent to the peer-to-peer computing system through each node device for information comparison and to provide accurate identity information. Based on this, the present invention can also minimize the possibility of identity tampering with a system.

[0112] Specifically, the peer-to-peer computing system determines the permissions of an object by verifying the authenticity of its identity information. In this system, node devices capable of acquiring identity information may choose not to provide the identity information (or may provide it depending on implementation requirements), but instead express the verification result in their own result data based solely on the verification requirements for the authenticity of the identity information within the received result data. That is, in this invention, even when a node device capable of acquiring identity information does not provide it, the verification result is expressed in its own result data based solely on the verification requirements for the authenticity of the identity information within the received result data.

[0113] When a node device in a peer-to-peer computing system that is capable of obtaining identity information does not provide identity information, the information source device that drives the provision of identity information establishes an encrypted information transmission channel with the input terminal of the node device that needs to obtain identity information, or establishes an encrypted information transmission channel using other network communication modes; and uses the identity information as one of the inputs of the node device.

[0114] When necessary, in order to meet the needs of other traditional computing modes for raw data, such as the need for evidence preservation in traditional evidence presentation, in this embodiment, the node settings can be equipped with a data storage device for storing the raw data sensed by the sensor.

[0115] In practical implementation, the node device can also be equipped with leakage protection and other functions in its power supply. The node device can also provide various communication interfaces, including fiber optic interfaces and wireless communication interfaces; it can also provide a data interface for connecting external storage devices. The node device can be powered by solar energy or mains power. When implemented outdoors, the node device can be installed on poles such as streetlights (without crossarms, mounted on the main pole, or integrated into the lampshade); in pole-less areas, if implemented indoors, it can be wall-mounted or integrated into the ceiling.

[0116] When this invention is implemented indoors and outdoors, the node devices, as artificial intelligence facilities installed in public spaces, can serve as digital economy infrastructure for urban clusters, providing 24 / 7 seamless coverage. Through collaborative computing across node devices, vehicle identification accuracy can be nearly 100% at any location within the coverage area, with location identification accuracy being related to sensor accuracy.

[0117] In this invention, the architecture of a peer-to-peer computing network comprises all nodes of the same type and function. Each node dynamically adjusts its data processing model in real time according to the network's consensus mechanism. The raw data collected by data acquisition devices (including sensors, cameras, etc.) connected to each node is processed and encrypted by the node according to its own data processing model, generating byte-level processing and encryption results (i.e., result data). This result data is then sent to other node devices (the computational and encryption results simultaneously received by the current node from other node devices are also considered part of the raw data collected by the current node). Therefore, the effect of the raw data sensed by each sensor propagates exponentially among a massive number of peer-to-peer node devices. If each node sends its result data to 100 surrounding node devices, after four units of time, hundreds of millions of node devices will be affected by the event sensed by that sensor. In this computing model, information is relatively symmetrical and immune to tampering and forgery. It fundamentally solves the inherent hidden dangers of traditional information technology, namely, the false, forged, and erroneous information caused by information asymmetry, which in turn become entry points for fraud and cyberattacks, as well as the problems of long cycles, poor accuracy, and poor adaptability in complex and integrated applications. In turn, it truly becomes an information infrastructure for comprehensive management of large areas and a digital economy infrastructure.

[0118] This invention utilizes deep learning technology to train data processing models for node devices via neural networks. Based on task performance requirements, these models receive result data from other node devices and real-time dynamic environmental changes captured by connected sensors. They then collaborate with other node devices to perform cognition and response. During this process, each node device automatically optimizes the computation, structure, and parameters of its own deep learning neural network (i.e., the corresponding data processing model), thereby achieving environmental adaptation and continuous evolution of the data processing model. In other words, in this invention, each node device automatically optimizes the computation, structure, and parameters of its data processing model each time it processes data and calculates results. That is, the data processing model changes its computation, structure, or parameters to achieve environmental adaptation and continuous evolution. Here, a change in the data processing model (i.e., no change) is one effect of optimization; even a change of zero (i.e., no change) can be considered a form of change.

[0119] In this invention, to accurately reflect the mutual influence between node devices and determine whether the data processing model of the current node device is suitable for its connected sensors and actuators, the data processing model loaded on the node device performs adaptive perceptual calculations on the data processing models of preceding node devices. Specifically, when a node device processes result data from other node devices, the adaptive perceptual calculations include verifying the result data of the current node device with that of other relevant node devices and / or verifying the historical result data of the current node device to obtain an adaptability value or as input to the adaptability judgment model. In this invention, based on collaborative computing, the results of the verification calculations are reflected in the result data of the node devices, enabling the result data of a series of nodes to drive the model training facility to make greater adjustments to the data processing model of the problematic node device. The implementation of the adaptability value can serve as an alternative to the aforementioned adjustment method based on collaborative computing.

[0120] When the data processing model of a certain node device cannot adapt to the sensors and actuators it is connected to, the adaptive value of its adaptive perception calculation has the following impact on the current result data of the current node device: a preset flag bit is assigned a value in the current result data of the current node device; or, other related node devices perform comprehensive calculations on the current result data of the current node device based on their own data processing models, and when the resulting data can be used as input by subsequent node devices, the resulting data is used by other node devices for calculation, driving the adjustment of the data processing model of the current node device.

[0121] For data processing models, adaptive perceptual computing is encompassed within other computing (including the calculation of result data, the adjustment of data processing models, etc.). In other words, a single round of computing includes both other types of computing and adaptive perceptual computing, meaning that adaptive perceptual computing and the calculation of result data are performed simultaneously.

[0122] In this invention, the adjustment of the data processing model occurs during the current calculation of the result data or during several data transfers and calculations of the result data. Specifically, the data processing model of the node device should cover the following modes:

[0123] Mode 1: When the adaptability value of a node device's data processing model exceeds a threshold, the node device's output data is added to the list of receiving nodes for the connected model training facility. Upon receiving this data, the connected node device will include a driving command for the model training facility in its current calculation result data. The threshold value can be a preset value or a dynamic value, depending on the implementation requirements. If the threshold value is dynamic, it is determined by a pre-set program or by a dynamically updated data processing model. In this invention, based on collaborative computing, the model training facility can be driven to adjust the data processing model of the problematic node device during the node device's calculation of the result data. The implementation of the driving command can serve as an alternative to the aforementioned collaborative computing-based adjustment method.

[0124] Mode 2: The model training facility is regarded as a type of sensor. The signals emitted by it are added to the connected node devices. After the node devices calculate and send out the result data, the corresponding node devices in the peer computing system will drive the data storage module of the connected sensor after calculating the result data. By establishing a file transfer channel between the node devices of the peer computing system or by establishing a file transfer channel through other network communication modes, the sensing data specified by the model training facility is sent to a specific location to participate in model training and improvement. The improved data processing model will be deployed in the same way to node devices that the original data processing model cannot adapt to.

[0125] In another implementation, the model training facility can also drive multiple node devices to generate new data processing models and update the data processing models by using their own perception data in a federated computing manner.

[0126] In this invention, each node device automatically optimizes its own data processing model's operations, structure, and parameters each time it processes data and calculates the result data. That is, the data processing model changes its own operations, structure, or parameters. These changes originate from the entire peer-to-peer computing system's comprehensive perception of various targets, events, and their combinations. Therefore, this change is a kind of "memory" of the entire peer-to-peer computing system for various targets, events, and their combinations, which can improve the computational effect of "recalling" and "tracing".

[0127] The above embodiments are merely illustrative of the present invention and are not intended to limit the invention. Any changes or modifications to the above embodiments based on the technical essence of the present invention will fall within the scope of the claims of the present invention.

Claims

1. A peer-to-peer computing system integrating storage and computing, characterized in that, It includes multiple node devices, each equipped with a data processing model. There is no hierarchy among the node devices. Each node device processes the collected raw data using its data processing model, calculates the result data, and selects other node devices to receive the result data based on preset rules or the data processing model. After receiving the result data, the selected other node devices use it as one of the collected raw data and calculate the result data of the current node device using their data processing model. The resulting data is a simplified transcoding result of a multidimensional matrix. Specifically, it involves simplifying and transcoding different types of perception data belonging to different targets collected by different sensors on the node device based on transcoding rules to obtain matching perception codes. Construct a multidimensional perception matrix based on the perception codes corresponding to all current raw data collected by the node devices; By combining the perceptual multidimensional matrix with the preceding result data in multidimensional matrix form, the current result data in multidimensional matrix form is calculated to represent the current comprehensive state of the target's current behavior, attributes, and state. Similarly, multiple node devices in a peer-to-peer computing system perform collaborative computation to discover events. Corresponding to the discovered events, the execution devices connected to the node devices that need to respond to the events execute responses based on the computational results. Simultaneously, the result data characterizes the sensing state perceived by the sensors connected to the node devices, the node devices' own state, and the device state of the execution devices connected to the node devices. Through the computation of the result data and the connections between the node devices, non-media storage of the sensing state perceived by the sensors connected to each node device, the self-state of each node device, and the device state of the execution devices connected to each node device is completed, and computational tasks are performed.

2. The integrated storage and computing peer-to-peer computing system according to claim 1, characterized in that, For a given node device, after each calculation to obtain the result data, other node devices are selected to receive the result data according to preset rules or data processing models; thus, the node devices in the peer-to-peer computing system have a dynamic connection relationship and no fixed connection relationship is set.

3. The storage-computing integrated peer-to-peer computing system according to claim 2, characterized in that, After the current node device receives the result data from the preceding node device, the connection between the current node device and the preceding node device is terminated. The current node device waits to be selected to receive result data from one or more other node devices, thus forming a dynamic connection relationship.

4. The storage-computing integrated peer-to-peer computing system according to claim 3, characterized in that, The method for transmitting result data between node devices is as follows: the current node device receives the previous result data output by the preceding node device, and calculates the current result data by combining it with the current raw data collected by the current node device, and transmits it to the subsequent node device; and so on, transmitting the result data between node devices. Among them, the current raw data represents the current state of the target's current behavior, attributes, state or event; the preceding result data represents the preceding comprehensive state of the target's preceding behavior, attributes, state or event; the current result data represents the current comprehensive state of the target's current behavior, attributes, state or event; and the current comprehensive state is the combination of the current state and the preceding comprehensive state.

5. The storage-computing integrated peer-to-peer computing system according to any one of claims 1 to 4, characterized in that, Different node devices collect raw data at their respective times and / or in their respective spaces. If it is necessary to trace the behavior, attributes, state, or event of a target, the current node device takes the need for target tracing as one of the inputs, and adds it to the calculation of the current result data along with other preceding result data and the current raw data, and then sends it to other node devices. Similarly, based on the preceding result data and the current raw data received by the current node device, the relationship between the preceding state value represented by the behavior, attributes, state, or event of the target in the raw data collected by the preceding node devices and the current state value represented by the current result data of the current node device is calculated, and non-media reading is completed through the calculation of the result data.

6. The storage-computing integrated peer-to-peer computing system according to claim 5, characterized in that, When there is an execution requirement, during the process of non-media storage or non-media retrieval, the node device takes the execution requirement as one of the inputs and calculates the result data; based on collaborative computing, it judges the business logic corresponding to the execution requirement and executes the business logic through the execution device connected to the node device.

7. The storage-computing integrated peer-to-peer computing system according to claim 1, characterized in that, Some or all of the node devices are equipped with at least one type of sensor to collect corresponding different types of sensing data, which is used to calculate and obtain the current result data.

8. The storage-computing integrated peer-to-peer computing system according to claim 7, characterized in that, If the current node device does not have one or more types of sensors set by the preceding node device, the current node device will still take the preceding result data containing the corresponding type of sensing data sent by the preceding node device as input and process it synchronously with the sensing data collected by the current node device's sensors.

9. The storage-computing integrated peer-to-peer computing system according to claim 1, characterized in that, Enumerate all perceptual abbreviations and their corresponding perceptual multidimensional matrices, and assign a specific abbreviation value to each perceptual multidimensional matrix; construct an M-bit N-ary sequence, where each bit of the N-ary sequence is assigned one of K different symbols; match each specific value of the M-bit N-ary sequence with each abbreviation value one by one; where the value of M×N is greater than the number of abbreviation values.

10. The storage-computing integrated peer-to-peer computing system according to claim 1, characterized in that, The result data obtained by the node device is represented in a multidimensional matrix as the data of the multidimensional matrix, the state value of the multidimensional matrix data, or the result of simplified transcoding of the multidimensional nested matrix data.

11. The storage-computing integrated peer-to-peer computing system according to claim 1, characterized in that, When node devices collect raw data, the raw data collected by each node device has corresponding time parameters and / or spatial parameters; time and / or space are used as dimensions in a multidimensional matrix.

12. The storage-computing integrated peer-to-peer computing system according to claim 11, characterized in that, Some or all of the node devices are equipped with at least one type of sensor to collect different corresponding types of sensing data; the sensors of the node devices perceive the target, and the sensing time is one dimension of the multidimensional matrix.

13. The storage-computing integrated peer-to-peer computing system according to claim 11, characterized in that, Some or all node devices are equipped with at least one type of sensor to collect different corresponding types of sensing data; each type of data sensed by each type of sensor is used as a dimension of a multidimensional matrix, or the types of sensors that meet the correlation conditions are combined as a dimension of a multidimensional matrix.

14. The storage-computing integrated peer-to-peer computing system according to claim 13, characterized in that, Sensors include one or more of the following: cameras, vibration sensors, lighting devices, electromagnetic devices, and elemental composition sensors.

15. The storage-computing integrated peer-to-peer computing system according to any one of claims 11 to 14, characterized in that, If time is used as a dimension in a multidimensional matrix, then all node devices will synchronize their time.

16. The storage-computing integrated peer-to-peer computing system according to claim 1, characterized in that, The current node device selectively sends the current result data to other specific node devices. The principle of selective sending is: based on preset fixed rules, dynamic rules, or a model trained by machine learning, the specific other node devices are determined.

17. The storage-computing integrated peer-to-peer computing system according to claim 16, characterized in that, The model trained through machine learning is a reinforcement training model based on the node itself, using the preceding result data of the node device as the annotation for reinforcement training.

18. The storage-computing integrated peer-to-peer computing system according to claim 16 or 17, characterized in that, The node device calculates the result data and then selects a node device from the list of communicably reachable nodes to send it, according to the principle of selective transmission.

19. The storage-computing integrated peer-to-peer computing system according to claim 1, characterized in that, The node device is equipped with one or more output modes, including hardware and software interface output, screen output, indicator light signals, and electromagnetic wave signals.

20. The storage-computing integrated peer-to-peer computing system according to claim 1, characterized in that, The resulting data is propagated and computed among the node devices in the peer-to-peer computing system, enabling the execution devices connected to the node devices to respond to one or more combinations of the behavior, attributes, states, or events of one or more targets.

21. The storage-computing integrated peer-to-peer computing system according to claim 20, characterized in that, If the execution device connected to the node device needs to obtain basic data from outside the peer computing system to make a response determination to one or more combinations of behaviors, attributes, states or events of one or more targets, the node device in the peer computing system that is connected to an accessible data acquisition device capable of obtaining basic data from outside the peer computing system will be driven to perform basic data acquisition, and the data acquired through accessible data acquisition will be used as input to the node device to participate in the calculation and obtain the current result data.

22. The storage-computing integrated peer-to-peer computing system according to claim 5, characterized in that, The peer-to-peer computing system is used to identify non-specific features of visitors requesting non-media reading; node devices set up at different collection locations collect at least one point sample of the visitor, and the point sample is the sensing data of the corresponding sensor type; Without needing to obtain the visitor's identity information, multiple node devices in the peer-to-peer computing system perform collaborative computation to determine that each unique visitor is itself, thus achieving non-specific feature recognition.

23. The storage-computing integrated peer-to-peer computing system according to claim 22, characterized in that, When it is necessary to obtain the identity information of visitors outside the peer-to-peer computing system, an identity information acquisition command is triggered. The identity information acquisition command is used as one of the inputs to participate in the calculation of the result data of the node device. By driving the node device in the peer-to-peer computing system that is connected to the barrier-free data collection conditions that can obtain the identity information of visitors outside the peer-to-peer computing system, the corresponding result data is responded to, thereby realizing the acquisition of the visitor's identity information.

24. The storage-computing integrated peer-to-peer computing system according to claim 23, characterized in that, Peer-to-peer computing systems determine access permissions by verifying the authenticity of a visitor's identity information. In this system, the node devices that can obtain identity information do not provide the identity information itself, but only express the verification results in the result data of the node device based on the verification requirements for the authenticity of the identity information in the received result data.

25. The storage-computing integrated peer-to-peer computing system according to claim 24, characterized in that, The peer-to-peer computing system verifies the visitor's true identity and ownership relationship to determine whether their true identity grants them the execution permissions required for the current request. Specifically, the peer-to-peer computing system directly performs collaborative calculations on actual behavior, trajectory, and data to determine the relationship between the visitor's true identity and the execution permissions required for the current request. Other node devices then perform subsequent calculations on the relationship between the true identity and the execution permissions obtained from the requester, and express the relationship between the requester's true identity and the execution permissions required for the current request in the result data, which is then transmitted to the next layer of subsequent node devices. It is not necessary to output the specific identity information of the requester to other node devices.

26. The storage-computing integrated peer-to-peer computing system according to claim 24, characterized in that, In a peer-to-peer computing system, the node device capable of obtaining identity information does not provide the identity information itself. Instead, the information source device that drives the provision of identity information establishes an encrypted information transmission channel with the node device input terminal that needs to obtain the identity information, or establishes an encrypted information transmission channel using other network communication modes, and uses the identity information as one of the inputs to the node device.

27. The storage-computing integrated peer-to-peer computing system according to claim 1, characterized in that, Each time the data processing model deployed on the node device processes data and calculates the result data, each node device automatically optimizes the operation, structure and parameters of its own data processing model to achieve environmental adaptation and continuous evolution of the data processing model; among them, changing the data processing model 0 is one of the effects of optimization.

28. The storage-computing integrated peer-to-peer computing system according to claim 1 or 27, characterized in that, The data processing model loaded on the node device performs adaptive perceptual computation on the data processing model of the preceding node device. Specifically, when a node device performs computational processing on the result data from other node devices, the adaptive perceptual computation includes verifying the result data of the current node device with that of other relevant node devices and / or verifying the historical result data of the current node device to obtain an adaptive value.

29. The storage-computing integrated peer-to-peer computing system according to claim 28, characterized in that, When the data processing model of a certain node device cannot adapt to the sensors and actuators it is connected to, the effect of its adaptive perception calculation on the current result data of the current node device is: in the current result data of the current node device, a preset flag bit is assigned a value. Alternatively, other relevant node devices can perform comprehensive calculations on the current result data of the current node device based on their own data processing models. The resulting data can be used as input by subsequent node devices. After the resulting data is used by other node devices for calculation, it drives the adjustment of the data processing model of the current node device.

30. The storage-computing integrated peer-to-peer computing system according to claim 28, characterized in that, In the current calculation of result data or in several data transmissions and calculations of result data, the data processing model of the node device covers the following patterns: When it is found that the fitness value of the data processing model of a certain node device exceeds the degree threshold, the output data of the node device will be added to the list of receiving nodes of the node device connected to the model training facility. When the node device connected to the model training facility receives such data, it will include the driving command for driving the model training facility in its current calculation result data. The model training facility is considered a type of sensor. The signals it emits are added to the connected node devices. After the node devices calculate and send out the result data, the corresponding node devices in the peer computing system, after calculating the result data, will drive the data storage module of the connected sensor to send the sensing data specified by the model training facility to a specific location by establishing a file transfer channel between the node devices of the peer computing system or by establishing a file transfer channel through other network communication modes. This will participate in model training and improvement. The improved data processing model will be deployed in the same way to node devices that the original data processing model cannot adapt to.

31. The storage-computing integrated peer-to-peer computing system according to claim 30, characterized in that, Alternatively, the model training facility can drive multiple node devices to generate new data processing models and update the data processing models through federated computing, using their own perception data.

32. The storage-computing integrated peer-to-peer computing system according to claim 30 or 31, characterized in that, The threshold value can be a set value or a dynamic value; if it is a dynamic value, it is determined by a pre-set program or by a dynamically updated data processing model.