Intelligence quality evaluation method, device and equipment for multi-source data fusion

Abstract

This disclosure provides a method, apparatus, and device for intelligence quality assessment based on multi-source data fusion. The method includes: in response to acquiring multi-source fused data, quantifying the multi-source fused data using a preset evaluation index system to obtain a standardized score; wherein the multi-source fused data is a synthesis of raw sensor data collected by multiple sensors; mapping the standardized score to a preset quality level using preset evaluation rules and initial weights matching the preset evaluation index system to generate an intelligence quality assessment result; wherein the intelligence quality assessment result includes a comprehensive evaluation result and subdivided index evaluation results matching the preset evaluation index system, and the preset quality level includes unqualified, qualified, and excellent. Using the method of this disclosure, the efficiency of intelligence quality assessment based on multi-source data fusion can be significantly improved, enabling timely support for command and decision-making.

Description

Technical Field

[0001] This disclosure relates to the field of multi-source data fusion technology, specifically to an intelligence quality assessment method, apparatus, and equipment for multi-source data fusion. Background Technology

[0002] With the development of information technology, multi-source data fusion technology, by comprehensively processing sensor data of different systems and types, generates more comprehensive and accurate intelligence information, effectively compensating for the limitations of single data sources in terms of coverage and accuracy. Intelligence quality directly affects system performance and decision-making effectiveness, especially in military and other fields, where high-quality intelligence is crucial for situational awareness and combat outcome. Therefore, intelligence quality assessment has become an indispensable part of information systems.

[0003] However, existing technologies have significant drawbacks. First, with the surge in the types and number of sensors, the amount of data that the system needs to process has increased dramatically, leading to a heavier computational burden. Furthermore, with the addition of new sensors, traditional methods struggle to efficiently integrate and automatically evaluate their data, resulting in low evaluation efficiency. Second, existing evaluations often focus on the final result, lacking fine-grained diagnostics of individual sensor performance, making it impossible to accurately pinpoint the sources of quality defects and hindering system optimization and performance improvement. In addition, when introducing new evaluation indicators, existing methods do not adequately consider their weighting, resulting in insufficient scalability of the evaluation system and affecting the scientific validity of the overall conclusions. These limitations restrict the application effectiveness of multi-source data fusion technology in dynamic and complex environments. Summary of the Invention

[0004] To address the aforementioned technical problems, the present disclosure provides a solution. Embodiments of this disclosure offer a method, apparatus, and device for assessing intelligence quality based on multi-source data fusion.

[0005] According to a first aspect of the present disclosure, an intelligence quality assessment method for multi-source data fusion is provided, wherein the method includes: In response to the acquisition of multi-source fusion data, the multi-source fusion data is quantified using a preset evaluation index system to obtain a standardized score; wherein, the multi-source fusion data is a synthesis of raw sensor data collected by multiple sensors; Using preset evaluation rules and initial weights matching the preset evaluation index system, the standardized score is mapped to a preset quality level to generate an intelligence quality evaluation result. The intelligence quality evaluation results include comprehensive evaluation results and subdivided indicator evaluation results that match the preset evaluation indicator system. The preset quality levels include unqualified, qualified, and excellent.

[0006] According to a second aspect of the present disclosure, an intelligence quality assessment apparatus for multi-source data fusion is provided, wherein the apparatus includes: The quantization processing unit is configured to: in response to acquiring multi-source fusion data, quantify the multi-source fusion data using a preset evaluation index system to obtain a standardized score; wherein the multi-source fusion data is a synthesis of raw sensor data collected by multiple sensors; The quality evaluation unit is configured to: map the standardized score to a preset quality level using preset evaluation rules and initial weights matching the preset evaluation index system, and generate an intelligence quality evaluation result; The intelligence quality evaluation results include comprehensive evaluation results and subdivided indicator evaluation results that match the preset evaluation indicator system. The preset quality levels include unqualified, qualified, and excellent.

[0007] According to a third aspect of the present disclosure, an electronic device is provided, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the intelligence quality assessment method for multi-source data fusion as described in the present disclosure.

[0008] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, the storage medium storing a computer program for executing the intelligence quality assessment method for multi-source data fusion described in the present disclosure.

[0009] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, it implements the intelligence quality assessment method for multi-source data fusion described in the present disclosure.

[0010] As described above, the intelligence quality assessment method for multi-source data fusion provided in this disclosure significantly improves the efficiency of intelligence quality assessment by constructing a multi-level intelligence quality evaluation index system and an automated processing flow, enabling timely support for command and decision-making. By designing a sensor impact factor calculation method, it accurately locates the sensor sources causing quality defects, providing a clear basis for system equipment optimization and performance improvement. Furthermore, by introducing a dynamic weight allocation mechanism, it effectively solves the problem of weight integration for newly added evaluation indicators, ensuring the objectivity and scalability of the system evaluation. Ultimately, it achieves closed-loop management from intelligence quality assessment and defect tracing to system optimization, comprehensively improving the reliability and practicality of the multi-source data fusion system. Attached Figure Description

[0011] The above and other objects, features, and advantages of this disclosure will become more apparent from the more detailed description of the embodiments thereof in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this disclosure and form part of the specification. They are used together with the embodiments of this disclosure to explain the disclosure and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0012] Figure 1 This is a flowchart illustrating an exemplary embodiment of the present disclosure of an intelligence quality assessment method for multi-source data fusion. Figure 2 This is a public announcement Figure 1 An exemplary flowchart of an intelligence quality assessment method for multi-source data fusion provided in this embodiment; Figure 3 This is a schematic diagram of the architecture of the "Multi-Source Data Fusion Intelligence Quality Assessment Index System" provided in an exemplary embodiment of this disclosure; Figure 4 This is a public announcement Figure 1 Another exemplary flowchart of the intelligence quality assessment method for multi-source data fusion provided in the embodiment; Figure 5 This is a public announcement Figure 1 Another exemplary flowchart of the intelligence quality assessment method for multi-source data fusion provided in the embodiment; Figure 6 This is a schematic diagram of a "membership function" provided in an exemplary embodiment of this disclosure; Figure 7 This is a public announcement Figure 1 Another exemplary flowchart of the intelligence quality assessment method for multi-source data fusion provided in the embodiments; Figure 8 This is a public announcement Figure 1 Another exemplary flowchart of the intelligence quality assessment method for multi-source data fusion provided in the embodiment; Figure 9 This is a schematic diagram of the structure of an intelligence quality assessment device for multi-source data fusion provided in an exemplary embodiment of the present disclosure; Figure 10 This is a schematic diagram of the structure of an application embodiment of the electronic device disclosed herein. Detailed Implementation

[0013] The present disclosure will be further described below with reference to the embodiments shown in the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present disclosure, and not all embodiments of the present disclosure. It should be understood that the present disclosure is not limited to the exemplary embodiments described herein.

[0014] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0015] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of this disclosure are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0016] It should also be understood that in the embodiments disclosed herein, "a plurality of" may refer to two or more, and "at least one" may refer to one, two or more.

[0017] It should also be understood that any component, data or structure mentioned in the embodiments of this disclosure can generally be understood as one or more unless expressly defined or given to the contrary in the context.

[0018] Furthermore, the term "and / or" in this disclosure is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this disclosure generally indicates that the preceding and following related objects have an "or" relationship.

[0019] It should also be understood that the description of the various embodiments in this disclosure emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0020] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0021] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0022] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0023] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0024] Overview of the inventive concept: Reference Figure 2The inventive concept of this disclosure is as follows: by establishing a closed-loop processing flow, firstly, multi-source independent data from different sensors are fused to form comprehensive intelligence; then, based on a preset index system, the overall quality score and grade of the fused intelligence are determined; if the quality is found to be substandard, the independent data of each sensor are traced back to the source, and the specific sensor source causing the quality defect is accurately located by calculating the residual and influencing factors; finally, the analysis results are fed back to the front end, thereby achieving an organic unity from macro-quality assessment to micro-root cause diagnosis, as well as continuous optimization of the multi-source data fusion system.

[0025] Based on the above inventive concept, this disclosure provides the following solutions according to the embodiments.

[0026] Example 1 Figure 1 This is a schematic flowchart of an intelligence quality assessment method based on multi-source data fusion, provided by an exemplary embodiment of this disclosure. The method can be executed on a server; wherein, the server may include, for example, a cloud service platform or a locally deployed server.

[0027] Specifically, refer to Figure 1 The intelligence quality assessment method for multi-source data fusion includes: S110. In response to acquiring multi-source fusion data, the multi-source fusion data is quantified using a preset evaluation index system to obtain a standardized score.

[0028] The multi-source fusion data is a synthesis of raw sensor data collected by multiple sensors.

[0029] Optionally, the preset evaluation index system (i.e., the multi-source data fusion intelligence quality assessment index system) includes at least timeliness indicators, continuity indicators, accuracy indicators, and reliability indicators.

[0030] Among them, timeliness indicators, continuity indicators, accuracy indicators, and reliability indicators can be used as primary indicators; the sub-indicators under the primary indicators can be used as secondary indicators.

[0031] In an optional specific example, refer to Figure 3 Under the multi-source data fusion intelligence quality assessment index system: The primary indicators include timeliness (P1), continuity (P2), accuracy (P3), and reliability (P4).

[0032] The secondary indicators under timeliness P1 include the time to first point discovery P. 11 (It should be noted here that P) 11 This refers to the standardized score corresponding to "first point discovery time." The P-values ​​for other indicators have similar meanings, referring to the standardized score corresponding to that indicator (not individually listed for simplicity). (Quantity determination time P)12 Type determination time P 13 Attribute determination time P 14 Secondary indicators under continuity P2 include the point loss rate P. 21 Temporary cancellation duration P 22 Vanishing distance P of the tail point 23 The secondary indicators under accuracy P3 include high precision P. 31 Distance accuracy P 32 Azimuth accuracy P 33 Speed ​​accuracy P 34 Type accuracy P 35 Quantity accuracy P 36 Attribute accuracy P 37 Accuracy of mixed batches and incorrect batches P 38 The secondary indicators under reliability P4 include the false alarm rate (P). 41 and false alarm P 42 .

[0033] Optionally, refer to Figure 4 Step S110, "quantifying the multi-source fusion data using a preset evaluation index system to obtain a standardized score," may include: S1110. Using the preset evaluation index system, identify each sub-index in the multi-source fusion data that corresponds to the preset evaluation index system. S1120. For each sub-index, perform dimension removal processing using a quantization algorithm matching that sub-index. The quantization algorithm includes at least the ratio method, the dichotomy method, and the error normalization method.

[0034] The following example illustrates the "quantification process" using detailed indicators: 1) Regarding the secondary indicators under timeliness.

[0035] Let the theoretical detection time of the target under fusion be... The actual time for the first point of target detection is... The standardized score for the first point discovery time can be calculated using the following formula:

[0036] The number of racks reported by the fusion center is quantified using the timeliness assessment method based on the first-point discovery time, resulting in a standardized score P corresponding to the quantity determination time. 12 .

[0037] The first-point time of the target type reported by the fusion center is used as the basis for quantifying the timeliness assessment of the first-point discovery time, resulting in a standardized score P corresponding to the type determination time. 13 .

[0038] The system uses the first-point time of target friend-or-foe attributes reported by the fusion center, and quantifies it according to the calculation method for the timeliness assessment of the first-point discovery time, to obtain the standardized rating corresponding to the attribute determination time. 14 .

[0039] 2) Regarding secondary indicators under continuity.

[0040] Fusion intelligence reports waypoints periodically, and the number of lost waypoints (including those that need to be replenished) is calculated. The waypoint loss rate is the ratio of the number of lost waypoints to the theoretically required total number of waypoints to be detected. The standardized score P corresponding to the waypoint loss rate is then calculated. 21 The calculation formula is:

[0041] in, To lose points, The total number of points to be detected is theoretically required.

[0042] For merged tracks identified as belonging to the same group of targets, the total duration of temporary cancellation of the merged tracks is set to be... The theoretical total detection time, from the initial discovery point to the disappearance of the tail point, is... The standardized score P corresponding to the temporary cancellation duration. 22 for:

[0043] Standardized score P corresponding to the vanishing distance of the tail point 23 for:

[0044] in, To determine the furthest distance at which the fusion center can detect the target, The farthest distance to fly towards the target.

[0045] 3) Regarding the secondary indicators under accuracy.

[0046] Let the height accuracy of the fusion detection be... The lower limit of the expected accuracy is The standardized score P corresponding to the height (detection) accuracy. 31 for:

[0047] Standardized score P corresponding to distance (detection) accuracy 32 Standardized score P corresponding to azimuth (detection) accuracy 33 Standardized score P corresponding to velocity (detection) accuracy 34 The calculation method is the same as above.

[0048] For the three sub-indicators of type accuracy, quantity accuracy, and attribute accuracy, a standardized score of 1 point is awarded for accurate judgment, and 0 points is awarded otherwise.

[0049] For the same target, the track number should remain unchanged throughout the discovery and tracking process. When the fusion center reports different track numbers for the same target, it is determined that the fusion report is incorrect. Mixed batch refers to the tracking errors of two batches of targets, resulting in confusion. When the number of incorrect / mixed batches is 0, the standardized score corresponding to the accuracy of the number of incorrect / mixed batches can be 1 point; otherwise, it is 0 points.

[0050] 4) Regarding secondary indicators under reliability.

[0051] Missed alarms refer to situations where the system fails to detect a target even when it is actually present. Let the number of fused missed alarms be... The expected lower limit for the number of missed warnings is The standardized score P corresponding to the missed alarm is... 41 for:

[0052] False alarms refer to situations where the system incorrectly identifies the presence of a target during the target detection process. The standardized scoring method for fusion false alarm assessment is consistent with the aforementioned method for missed alarm assessment.

[0053] S120. Using preset evaluation rules and the initial weights matching the preset evaluation index system, the standardized score is mapped to a preset quality level to generate an intelligence quality evaluation result.

[0054] The intelligence quality evaluation results include comprehensive evaluation results and subdivided indicator evaluation results that match the preset evaluation indicator system. The preset quality levels include unqualified, qualified, and excellent.

[0055] Optionally, the initial weights include a primary weight vector corresponding to the primary indicator and a sub-weight vector corresponding to the sub-indicator; each primary indicator includes at least one sub-indicator.

[0056] Optionally, refer to Figure 5 Step S120 may include the following steps: S1210. Construct a membership function corresponding to the preset evaluation index system.

[0057] Specifically, based on fuzzy mathematics theory, a system is established for the preset quality levels (unqualified, qualified, excellent) as follows: Figure 6The piecewise linear membership function shown maps standardized scores (ranging from 0 to 1) to membership values ​​for three quality levels. For example, for the "Excellent" level, a score above 0.8 represents full membership (membership 1), scores increase linearly between 0.6 and 0.8 (from 0 to 1), and scores below 0.6 represent no membership (membership 0). Differentiated mappings for different indicators are achieved through function parameterization.

[0058] It should be noted that the above embodiments employ fuzzy hierarchical analysis (AHP) based on fuzzy mathematics theory. This method can quantify factors with unclear boundaries and difficulty in quantification based on fuzzy relation synthesis, and then perform a comprehensive evaluation. AHP is advantageous in handling complex systems composed of numerous interconnected and mutually constraining factors lacking quantitative data. It combines qualitative and quantitative methods to process various indicator factors, possessing the advantages of being systematic, flexible, and concise, and is widely used in fields such as scheme selection and performance evaluation.

[0059] S1220. Using the membership function, the standardized score of each sub-indicator is converted into a membership value belonging to different quality levels, which is used as the evaluation result of the sub-indicator.

[0060] Specifically, the standardized score of each sub-indicator is input into its corresponding membership function to calculate the degree to which the score belongs to the three quality levels. Taking the high precision indicator (score 0.85) as an example, the membership vector [0.1, 0.3, 0.9] is calculated through the membership function, indicating that the indicator has a 10% probability of being unqualified, a 30% probability of being qualified, and a 90% probability of being excellent (Note: Fuzzy membership can be greater than 1, but needs to be normalized).

[0061] In a specific example, taking the "timeliness" indicator as an example, the membership matrix as follows:

[0062] Similarly, the membership matrices for continuity, accuracy, and reliability indices can be obtained. .

[0063] S1230. Based on the subdivided weight vector and the membership value, generate a first-level comprehensive evaluation result vector corresponding to each first-level indicator of the preset evaluation index system.

[0064] In a specific example, a fuzzy weighted average algorithm can be used to synthesize the membership values ​​of all sub-indicators under the same primary indicator with their sub-weight vectors.

[0065] For example, the membership matrix of the four sub-indicators under the timeliness indicator. With the corresponding subdivision weight vector Fuzzy synthesis is performed to obtain the first-level comprehensive evaluation result vector B1 corresponding to the timeliness index. Similarly, the membership degree matrices for the continuity, accuracy, and reliability indices are also obtained. With the corresponding subdivision weight vector Fuzzy synthesis is performed to obtain the first-level comprehensive evaluation result vectors B2~B4, corresponding to the continuity, accuracy, and reliability indices, respectively. These are expressed by the following formulas:

[0066] in, This represents a matrix composed of vectors representing the results of each first-level comprehensive evaluation.

[0067] S1240. By using fuzzy synthesis operation, each first-level comprehensive evaluation result vector is aggregated with the corresponding first-level weight vector to obtain the final evaluation result vector of each first-level indicator.

[0068] Specifically, aggregation calculations can be performed using the following formula:

[0069] Where B represents the final evaluation result vector. W 1 represents the first-level weight vector corresponding to B1; W 2 represents the first-level weight vector corresponding to B2; W 3 represents the first-level weight vector corresponding to B3; W 4 represents the first-level weight vector corresponding to B4.

[0070] S1250. Determine the comprehensive evaluation result based on the maximum membership value in the final evaluation result vector.

[0071] The preset quality levels include unqualified, qualified, and excellent.

[0072] In a specific example, the quality level is determined based on the maximum membership value in the final evaluation result vector B. Assuming B = [0.15, 0.25, 0.60], the maximum membership value of 0.60 corresponds to the "excellent" level, and the system determines the fused intelligence to be of excellent quality. Simultaneously, the evaluation results at each level are output, providing a basis for quality optimization decisions.

[0073] Based on the above embodiments, optionally, refer to Figure 7 The intelligence quality assessment method described in this disclosure also includes: S710. In response to determining that there is a non-compliant sub-indicator based on the evaluation results of the sub-indicator, calculate the influence factor of each of the multiple sensors on the non-compliant sub-indicator.

[0074] In a specific example, step S710 can be implemented through the following steps: I1. Calculate the measurement error of each sensor under the specified non-compliance sub-index.

[0075] Specifically, when the system detects that a specific sub-indicator is deemed unqualified, it first retrieves the set of raw observation data reported by each sensor within the evaluation period of that indicator from the data cache. Then, it reads the optimal estimate generated by the fusion center based on multi-source data fusion as a reference benchmark. Finally, for each sensor, the absolute deviation between its observed value and the reference benchmark is calculated; this deviation is the measurement error of that sensor under this unqualified indicator. The entire process ensures that error calculation is based on a unified spatiotemporal benchmark.

[0076] I2. Based on the preset fusion weight of each type of sensor participating in the fusion, the measurement error matched with that type of sensor is weighted and calculated to obtain the weighted residual.

[0077] Specifically, the system retrieves the weight allocation values ​​for each sensor in the data fusion process from a preset configuration library. These weights reflect the relative importance of different sensors in the fusion system. The measurement error of each sensor is multiplied by its corresponding fusion weight to obtain a weighted residual value. This step ensures that the errors of highly important sensors are amplified, while the errors of less important sensors are correspondingly reduced, thus more accurately reflecting the actual impact of each sensor on the overall quality.

[0078] I3. Based on the weighted residuals, sort each of the multiple sensors in ascending order, and assign a serial number score to each sensor as the current score.

[0079] Specifically, all sensors are sorted in ascending order according to their calculated weighted residual values, resulting in a sensor sequence from best to worst performance. Based on the sorting results, each sensor is assigned a corresponding score using a sequential coding method, with the first-ranked sensor receiving 1 point, the second-ranked sensor receiving 2 points, and so on. This score reflects the sensor's performance relative to other sensors within the current evaluation period; a lower score indicates better performance in that non-compliant indicator.

[0080] I4. In response to obtaining the historical serial number scores and historical statistical counts of the various sensors, determine the influence factor of each sensor based on the historical serial number scores, historical statistical counts, and the current score.

[0081] Specifically, the system maintains a historical database that continuously records the serial number score and total number of times each sensor participated in the statistics across all evaluations. Upon receiving a new current score, the system first updates the sensor's cumulative historical score and the number of times it participated in the statistics. Then, an impact factor is calculated based on the historical data. This factor is obtained by normalizing the sum of historical scores to the number of times the sensors were used and the total number of sensors. A smaller impact factor value indicates better long-term performance from the sensor and a greater positive contribution to system quality; conversely, a larger impact factor value indicates performance defects in the sensor that require optimization.

[0082] S720. Based on the influencing factors, determine the sensor that causes the non-conforming sub-indicator and record it as the source of quality defect.

[0083] Specifically, the influencing factors are statistically analyzed, and the sensor corresponding to the maximum value of the influencing factor is taken as the sensor that caused the non-compliance sub-index.

[0084] Based on the above embodiments, optionally, refer to Figure 8 The intelligence quality assessment method described in this disclosure also includes: S810. In response to obtaining the new evaluation indicator, construct a new evaluation indicator system using the new evaluation indicator and the preset evaluation indicator system; S820. Determine the weight of each sub-indicator in the new evaluation indicator system using the dynamic weight allocation principle.

[0085] In a specific example, step S820 may further include: Step 1: Maintain the first relative weight ratio among the sub-indicators in the preset evaluation index system unchanged. Step 2: In response to obtaining the second relative weight ratio among the sub-indicators in the sampled sub-index sequence, determine the third relative weight ratio among the sub-indicators in the new evaluation index system using the first and second relative weight ratios. The sampled sub-index sequence includes sub-indicators sampled from the preset evaluation index system and sub-indicators sampled from the newly added evaluation indicators. Step 3: Based on the third relative weight ratio, calculate the weight of each sub-index in the new evaluation index system using normalization.

[0086] For example, suppose the pre-set evaluation index system originally has 5 indicators a1, a2, a3, a4, and a5, with weights of 0.1, 0.15, 0.3, 0.2, and 0.25 respectively; and new evaluation indicators a6 and a7 are added, with expert evaluations assigning weights of a1, a2, a6, and a7 (i.e., the sampled sub-indicator sequence) of 0.1, 0.15, 0.55, and 0.2 respectively. Based on the above example, the following operations can be performed: 1) Retain the relative proportions of a1, a2, a3, a4, and a5 as 2:3:6:4:5; 2) Determine the relative proportions of a1, a2, a6, and a7 as 2:3:11:4; 3) Determine the relative proportions of a1, a2, a3, a4, a5, a6, and a7 in the new evaluation index system as 2:3:6:4:5:11:4; 4) Perform normalization calculation, i.e., 2k + 3k + 6k + 4k + 5k + 11k + 4k = 1, obtaining k = 1 / 35; 5) Based on the value of k, calculate the weights of each sub-indicator in the new evaluation index system, i.e., w 1 = 0.07; w 2 = 0.09; w 3 = 0.17; w 4 = 0.11; w 5 = 0.14; w 6 = 0.31; w 7 = 0.11.

[0087] As described above, the intelligence quality assessment method for multi-source data fusion provided in this disclosure significantly improves the efficiency of intelligence quality assessment by constructing a multi-level intelligence quality evaluation index system and an automated processing flow, enabling timely support for command and decision-making. By designing a sensor impact factor calculation method, it accurately locates the sensor sources causing quality defects, providing a clear basis for system equipment optimization and performance improvement. Furthermore, by introducing a dynamic weight allocation mechanism, it effectively solves the problem of weight integration for newly added evaluation indicators, ensuring the objectivity and scalability of the system evaluation. Ultimately, it achieves closed-loop management from intelligence quality assessment and defect tracing to system optimization, comprehensively improving the reliability and practicality of the multi-source data fusion system.

[0088] Example 2 It should be understood that the intelligence quality assessment method for multi-source data fusion described in the foregoing embodiments herein can also be similarly applied to the intelligence quality assessment apparatus for multi-source data fusion for similar extensions. For simplicity, it is not described in detail.

[0089] Figure 9 This is a schematic diagram of an intelligence quality assessment device for multi-source data fusion provided in an exemplary embodiment of this disclosure. (Refer to...) Figure 9 The device includes: The quantization processing unit 910 is configured to: in response to acquiring multi-source fusion data, quantize the multi-source fusion data using a preset evaluation index system to obtain a standardized score; wherein the multi-source fusion data is a synthesis of raw sensing data collected by multiple sensors.

[0090] The quality evaluation unit 920 is configured to: map the standardized score to a preset quality level using preset evaluation rules and initial weights matching the preset evaluation index system, and generate an intelligence quality evaluation result.

[0091] The intelligence quality evaluation results include comprehensive evaluation results and subdivided indicator evaluation results that match the preset evaluation indicator system. The preset quality levels include unqualified, qualified, and excellent.

[0092] As described above, the intelligence quality assessment device for multi-source data fusion provided in this disclosure significantly improves the efficiency of intelligence quality assessment by constructing a multi-level intelligence quality evaluation index system and an automated processing flow, enabling timely support for command and decision-making. By designing a sensor impact factor calculation method, it accurately locates the sensor sources causing quality defects, providing a clear basis for system equipment optimization and performance improvement. Furthermore, by introducing a dynamic weight allocation mechanism, it effectively solves the problem of weight integration for newly added evaluation indicators, ensuring the objectivity and scalability of the system evaluation. Ultimately, it achieves closed-loop management from intelligence quality assessment and defect tracing to system optimization, comprehensively improving the reliability and practicality of the multi-source data fusion system.

[0093] Example 3 In addition, this disclosure also provides an electronic device, including: a memory for storing a computer program; and a processor for executing the computer program stored in the memory, wherein when the computer program is executed, it implements the intelligence quality assessment method for multi-source data fusion described in any of the above embodiments of this disclosure.

[0094] Figure 10 This is a schematic diagram of the structure of an application embodiment of the electronic device disclosed herein. Below, reference is made to… Figure 10 This describes an electronic device according to embodiments of the present disclosure. The electronic device may be either or both of a first device and a second device, or a standalone device independent of them, which may communicate with the first device and the second device to receive acquired input signals from them.

[0095] like Figure 10As shown, the electronic device includes one or more processors and memory. The processor may be a central processing unit (CPU) or other processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. The memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor may execute the program instructions to implement the intelligence quality assessment method for multi-source data fusion described in the various embodiments of this disclosure above, and / or other desired functions.

[0096] In one example, the electronic device may further include input and output devices, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown). Furthermore, the input device may include, for example, a keyboard, a mouse, etc. The output device can output various information to the outside, including determined distance information, direction information, etc. The output device may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0097] Of course, for the sake of simplicity, Figure 10 Only some of the components of the electronic device relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device may include any other suitable components depending on the specific application.

[0098] In addition to the methods and apparatus described above, embodiments of this disclosure may also be computer program products comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the intelligence quality assessment method for multi-source data fusion according to various embodiments of this disclosure as described in the foregoing portion of this specification.

[0099] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this disclosure. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0100] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the intelligence quality assessment method for multi-source data fusion according to various embodiments of this disclosure as described in the foregoing portion of this specification.

[0101] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0102] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as ROM, RAM, magnetic disk, or optical disk.

[0103] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0104] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0105] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0106] The methods and apparatus of this disclosure may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this disclosure are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, this disclosure may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this disclosure. Thus, this disclosure also covers recording media storing programs for performing the methods according to this disclosure.

[0107] It should also be noted that in the apparatus, devices, and methods of this disclosure, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions to this disclosure.

[0108] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0109] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. An intelligence quality evaluation method for multi-source data fusion, characterized in that, The method includes: In response to the acquisition of multi-source fusion data, the multi-source fusion data is quantified using a preset evaluation index system to obtain a standardized score; wherein, the multi-source fusion data is a synthesis of raw sensor data collected by multiple sensors; Using preset evaluation rules and initial weights matching the preset evaluation index system, the standardized score is mapped to a preset quality level to generate an intelligence quality evaluation result. The intelligence quality evaluation results include comprehensive evaluation results and subdivided indicator evaluation results that match the preset evaluation indicator system. The preset quality levels include unqualified, qualified, and excellent.

2. The method of claim 1, wherein, The preset evaluation index system includes at least timeliness, continuity, accuracy, and reliability indicators; The timeliness indicators include the time of first point discovery, the time of quantity determination, the time of type determination, and the time of attribute determination. The continuity indicators include the point loss rate, temporary cancellation duration, and tail point disappearance distance; The accuracy indicators include altitude accuracy, distance accuracy, orientation accuracy, speed accuracy, type accuracy, quantity accuracy, attribute accuracy, and the accuracy of the number of incorrect or mixed batches. The reliability metrics include missed alarms and false alarms.

3. The method of claim 1, wherein, The quantitative processing of the multi-source fusion data using a preset evaluation index system includes: Using the preset evaluation index system, identify the sub-indicators in the multi-source fusion data that correspond to the preset evaluation index system; For each sub-indicator, the dimensionality is removed using a quantification algorithm that matches that sub-indicator. The quantization algorithm includes at least the ratio method, the binary method, and the error normalization method.

4. The method according to claim 3, characterized in that, The initial weights include the primary weight vectors corresponding to the primary indicators and the sub-weight vectors corresponding to the sub-indicators; each primary indicator includes at least one sub-indicator. Using preset evaluation rules and initial weights matching the preset evaluation index system, the standardized score is mapped to a preset quality level to generate an intelligence quality evaluation result, including: Construct a membership function corresponding to the preset evaluation index system; Using the membership function, the standardized score of each sub-indicator is converted into a membership value belonging to different quality levels, which is used as the evaluation result of the sub-indicator. Based on the subdivided weight vector and the membership value, a first-level comprehensive evaluation result vector corresponding to each first-level indicator of the preset evaluation index system is generated; By aggregating each first-level comprehensive evaluation result vector with its corresponding first-level weight vector through fuzzy synthesis operation, the final evaluation result vector of each first-level indicator is obtained. The comprehensive evaluation result is determined based on the maximum membership value in the final evaluation result vector.

5. The method of claim 1, wherein, The method further includes: In response to determining that there are unqualified sub-indicators based on the evaluation results of the sub-indicators, the influence factor of each of the multiple sensors on the unqualified sub-indicators is calculated. Based on the aforementioned influencing factors, the sensors that cause the aforementioned non-conforming sub-indicators are identified and denoted as the sources of quality defects.

6. The method of claim 5, wherein, Calculate the influence factor of each of the multiple sensors on the non-compliance sub-indicator, including: Calculate the measurement error of each sensor under the specified non-compliance sub-indicator; Based on the preset fusion weight for each type of sensor participating in the fusion, the measurement error matched with that type of sensor is weighted and calculated to obtain the weighted residual. Based on the weighted residuals, each of the multiple sensors is sorted in ascending order, and each sensor is assigned a serial number and score as the current score. In response to obtaining the historical serial number scores and historical statistical counts of the various sensors, the influence factor of each sensor is determined based on the historical serial number scores, historical statistical counts, and the current score.

7. The method of claim 1, wherein, The method further includes: In response to the acquisition of new evaluation indicators, a new evaluation indicator system is constructed using the new evaluation indicators and the preset evaluation indicator system. The weights of each sub-indicator in the new evaluation index system are determined by using the principle of dynamic weight allocation.

8. The method of claim 7, wherein, Using the principle of dynamic weight allocation, the weights of each sub-indicator in the new evaluation index system are determined, including: The first relative weight ratio among the sub-indicators in the preset evaluation index system remains unchanged; In response to obtaining the second relative weight ratio among the sub-indicators in the sampled sub-indicator sequence, the third relative weight ratio among the sub-indicators in the new evaluation index system is determined using the first relative weight ratio and the second relative weight ratio; wherein, the sampled sub-indicator sequence includes sub-indicators sampled from the preset evaluation index system and sub-indicators sampled from the newly added evaluation index. Based on the third relative weight ratio, the weights of each sub-indicator in the new evaluation index system are obtained by normalization calculation.

9. An intelligence quality assessment device for multi-source data fusion, characterized by, The device includes: The quantization processing unit is configured to: in response to acquiring multi-source fusion data, quantify the multi-source fusion data using a preset evaluation index system to obtain a standardized score; wherein the multi-source fusion data is a synthesis of raw sensor data collected by multiple sensors; The quality evaluation unit is configured to: map the standardized score to a preset quality level using preset evaluation rules and initial weights matching the preset evaluation index system, and generate an intelligence quality evaluation result; The intelligence quality evaluation results include comprehensive evaluation results and subdivided indicator evaluation results that match the preset evaluation indicator system. The preset quality levels include unqualified, qualified, and excellent.

10. An electronic device, comprising: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the intelligence quality assessment method for multi-source data fusion as described in claims 1 to 8.

Images