A knowledge-based reasoning-based autonomous planning method and platform for instrument test processes

Abstract

The present invention relates to a method and platform for autonomous planning of instrument test processes based on knowledge reasoning. The method comprises the following steps: S1-acquisition of instrument test process knowledge, S2-construction of instrument test knowledge graph, and S3-intelligent determination of test processes based on autonomous rules. The platform is used for steps S1 to S3 in the method, and ultimately outputs the generated instrument test process plan or uses traditional manual methods to perform instrument test determination results. The method for autonomous planning of instrument test processes based on knowledge reasoning proposed in the present invention and the platform thereof overcome the defects of low efficiency of existing test instruments, equipment, means and methods, and unsatisfactory interpretability of results. The method is applied to instrument performance testing, and provides a reliable instrument test process planning scheme under highly interpretable conditions, thereby improving the reliability of the test results while improving the detection efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of instrument detection, and in particular to a method and platform for autonomous planning of an instrument test process based on knowledge reasoning. Background Art

[0002] Instrument testing technology plays a vital role in the development of modern science and technology. Before large-scale systems are put into operation, key instrument functions and indicators must be tested to ensure safe and reliable operation. Currently, there are two main methods for testing instrumentation: one relies on traditional methods, manually consulting equipment manuals and then manually testing system instruments against test procedures. This method is inefficient and labor-intensive. The other method uses deep learning methods such as neural networks to recommend instrument test procedures. This method is efficient but lacks interpretability, making it difficult to guarantee the reliability requirements of instrument test results.

[0003] Chinese patent (CN201710546649.7) provides a business process recommendation method based on convolutional neural networks, which manually obtains a large number of process files, obtains a process subgraph data set after preprocessing, and then uses a neural network model for sample training to achieve business process recommendation. Although this method and similar methods have improved the reliability of the test results to a certain extent, since the neural network is a black box model and the process file data information is fragmented, it is difficult to ensure the efficient learning of the neural network, and the interpretability is still not ideal. Chinese patent CN202210731921.X discloses a testing method, a testing system and a computer-readable storage medium, which creates a test environment by occupying space in a Java card, and performs system testing according to a pre-set test process. This method and similar methods still belong to the manual construction of the system test process, and fail to provide a test recommendation visualization function, so it is difficult to ensure efficient testing of the instrument. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the shortcomings of existing testing instruments, equipment, methods, and approaches, such as low efficiency and unsatisfactory interpretability of results. This invention provides a method for autonomously planning instrument test processes based on knowledge reasoning. This method, applied to instrument performance testing, provides a reliable instrument test process planning solution while ensuring highly interpretable results, thereby improving both testing efficiency and the reliability of test results. The present invention also provides an application platform based on this method.

[0005] The method for autonomous planning of instrument test processes based on knowledge reasoning proposed in the present invention comprises the following steps:

[0006] S1 - Instrument test process knowledge acquisition: Obtain user manuals for various types of test instruments, filter and extract knowledge text data from them as data sources; perform structured processing on the acquired knowledge text data, extract knowledge entities and entity relationships, and construct knowledge data of head entities, relationships, and tail entities for instrument testing; use the extracted triple knowledge data to establish entity node sets and entity relationship sets, and store them in dictionary form as JSON files;

[0007] S2-Construction of instrument test knowledge graph: Using the JavaScript-based visualization package D3.js, by reading the JSON file generated in step S1, the entity node data and entity relationship data constructed in step S1 are visualized in a graph, where each type of test instrument graph is displayed separately; the query target information is searched in the head entity and the tail entity of the entity relationship data set, and a new relationship set is established after matching. Then, based on the head entity and the tail entity in the newly established relationship set, a corresponding entity node set is constructed; using the logical knowledge reasoning method, the test process information of the target instrument test item is extracted and inferred from all the information; using the knowledge reasoning rule framework, the test process nodes are extracted and matched in the newly constructed entity relationship data set containing all the query target information, and the instrument test process plan is generated through test process reasoning;

[0008] S3- Intelligent judgment of test process based on autonomous rules: Establish an autonomous rule base for test instrument process. The rule items in the rule base are judged one by one according to the order of the instrument test process plan generated in step S2 until all rules are exhausted. The confidence of the overall instrument test process is calculated according to the following formula (1):

[0009]

[0010] In the above formula, J(i) represents the confidence of the overall planning process of test item i; s i Represents step x in test item i i ; n is the number of process steps in the process sequence of test item i; if the confidence is greater than the preset threshold, it is determined that the instrument test process planning is adopted.

[0011] Furthermore, the knowledge text data described in step S1 includes text data of instrument models and various performance indicators, detection process methods, and fault detection methods.

[0012] Furthermore, the triple knowledge data described in step S1 includes head entity, relationship, and tail entity data, wherein the head entity and tail entity data correspond to instrument detection parameters; and the relationship data corresponds to the specific relationship or attributes between the entity data.

[0013] Furthermore, in the dictionary form storage described in step S1, the dictionary keys include head entity, tail entity, relationship, and key value length, and the dictionary values ​​are the head entity name, tail entity name, relationship name, and length value corresponding to the above keys.

[0014] Furthermore, the confidence level in step S3 is used to determine whether to adopt the instrument test process plan output in step S2. If the confidence level is less than a threshold, the instrument test process plan is discarded and the instrument test is performed using a traditional manual method.

[0015] This knowledge-based reasoning-based instrument test process autonomous planning platform includes an instrument model selection function module, an instrument test item selection function module, an instrument test knowledge graph display function module, and an instrument test process planning recommendation function module, which is used to implement steps S1 to S3 in the above-mentioned knowledge-based reasoning-based instrument test process autonomous planning method, and finally output the generated instrument test process plan or use traditional manual methods to perform instrument test judgment results.

[0016] This invention proposes a method for autonomously planning instrument test processes based on knowledge reasoning. This method overcomes the shortcomings of existing testing instruments, equipment, and methods, such as low efficiency and suboptimal interpretability of results. Applied to instrument performance testing, this method provides a reliable instrument test process planning solution with high interpretability, thereby improving both testing efficiency and the reliability of test results. The invention also provides an application platform based on this method. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The following is a further description of an instrument test process autonomous planning method based on knowledge reasoning according to the present invention with reference to the accompanying drawings:

[0018] Figure 1 This is a flowchart of the steps of the autonomous planning method of the instrument test process based on knowledge reasoning;

[0019] Figure 2 It is a flow chart for constructing the instrument test knowledge graph described in step S1 of the instrument test process autonomous planning method based on knowledge reasoning;

[0020] Figure 3 It is the dictionary storage format described in step S1 of the present knowledge reasoning-based instrument test process autonomous planning method;

[0021] Figure 4 It is a flowchart for constructing the instrument test knowledge graph described in step S2 of the present knowledge reasoning-based instrument test process autonomous planning method;

[0022] Figure 5 It is a flowchart of the instrument test item process planning described in step S2 of the present knowledge reasoning-based instrument test process autonomous planning method;

[0023] Figure 6 This is a flow chart of the intelligent judgment of the test process described in step S3 of the present knowledge reasoning-based instrument test process autonomous planning method;

[0024] Figure 7 This is the logical structure wireframe diagram of the instrument test process autonomous planning platform based on knowledge reasoning. DETAILED DESCRIPTION

[0025] In the present invention, unless otherwise expressly specified or limited, terms such as "mounted," "connected," "connect," and "fixed" should be understood broadly. For example, they may refer to fixed connection, detachable connection, or integration; they may refer to direct connection or indirect connection through an intermediate medium; they may refer to internal communication between two components or interaction between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0026] In the description of the present invention, it should be understood that the terms "left", "right", "front", "back", "top", "bottom", "inside", "outside", etc., indicating directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they cannot be understood as limiting the present invention.

[0027] The technical solutions of the present invention are further described below with reference to specific embodiments, but the protection scope of the present invention is not limited to the following embodiments.

[0028] Implementation method: Figure 1 As shown, the method for autonomous planning of instrument test process based on knowledge reasoning includes the following steps:

[0029] S1-Instrument test process knowledge acquisition: e.g. Figure 2As shown, the user manuals of various types of test instruments are obtained, and the knowledge text data therein are screened and extracted as the data source; the obtained knowledge text data is structured, and knowledge entities and entity relationships are extracted to construct the head entity, relationship, and tail entity triple knowledge data of the instrument test; the extracted triple knowledge data are used to establish an entity node set and an entity relationship set, and stored as a JSON file in the form of a dictionary; the knowledge text data includes text data of the instrument model and various performance indicators, detection process methods, and fault detection methods; the triple knowledge data includes head entity, relationship, and tail entity data, wherein the head entity and tail entity data correspond to instrument detection parameters, such as instrument model, instrument performance indicators, detection link name, etc.; the relationship data corresponds to the specific relationship or attribute between entity data, such as detection indicator type, operation process sequence, etc.; as Figure 3 As shown, in the dictionary form storage described in step S1, the dictionary keys include head entity, tail entity, relationship, and key value length, and the dictionary values ​​are the head entity name, tail entity name, relationship name, and length value corresponding to the above keys.

[0030] S2-Instrument test knowledge graph construction: Figure 4 As shown, by using the JavaScript-based visualization package D3.js, the entity node data and entity relationship data constructed in step S1 are visualized by reading the JSON file generated in step S1, wherein each type of test instrument graph is displayed separately; the query target information is searched in the head entity and the tail entity of the entity relationship data set, and a new relationship set is established after matching, and then the corresponding entity node set is constructed according to the head entity and the tail entity in the newly established relationship set; the test process information of the target instrument test item is extracted and inferred from all the information using the logical knowledge reasoning method; the test process node extraction and matching is performed in the newly constructed entity relationship data set containing all the query target information using the knowledge reasoning rule framework, and the instrument test process plan is generated after the test process reasoning; wherein, the specific process of generating the instrument test process plan is as follows Figure 5 As shown, Figure 5In the example, "test step (x, y1)" is a predicate representation, indicating that the test step of test item "x" is "y1"; "next step (y1, y2)" indicates that the next operation after "y1" is "y2". By establishing knowledge reasoning rules based on this, the instrument test process can be inferred based on the entity relationship dataset and visualized in a graph, completing the process planning of the target instrument test project. At this point, the newly constructed data set contains all information about the query target. It establishes a graph knowledge query matching and reasoning mechanism to achieve autonomous test process planning for the target test items of the specified instrument model. By constructing an instrument test knowledge graph, knowledge reasoning methods are used to recommend instrument target test processes and provide a visual graph of the instrument test process, improving the interpretability of the test process recommendation method and increasing the credibility of the test process.

[0031] S3- Intelligent judgment of test process based on autonomous rules: Figure 6 As shown, a test instrument process autonomous rule base is established, and the rule items in the rule base are judged one by one according to the order of the instrument test process plan generated in step S2 until all rules are completed. Figure 6 In the rule base, "x1->x2" means that step "x1" occurs before step "x2". The confidence of the overall instrument test process is calculated according to the following formula (1):

[0032]

[0033] In the above formula, J(i) represents the confidence of the overall planning process of test item i; s i Represents step x in test item i i , where n is the number of process steps in the process sequence for test item i. If the confidence level is greater than a preset threshold, the instrument test process plan is adopted. The confidence level is used to determine whether to output the instrument test process plan in step S2. If the confidence level is less than the threshold, the instrument test process plan is discarded and the instrument test is performed using traditional manual methods. The judgment threshold in the scheme can be customized based on actual application conditions. This achieves intelligent judgment of the instrument test process and improves the reliability of the instrument test process plan.

[0034] Example: Figure 7As shown, the knowledge-based reasoning-based instrument test process autonomous planning platform proposed by the present invention includes an instrument model selection function module, an instrument test item selection function module, an instrument test knowledge graph display function module, and an instrument test process planning recommendation function module, which is used to implement steps S1 to S3 of the knowledge-based reasoning-based instrument test process autonomous planning method described in the above embodiment, and ultimately generate and output the instrument test process plan or use traditional manual methods to perform instrument test judgment results. Specifically, a software web platform for autonomous instrument test process planning is developed, and the text data generated in step S1 is used to construct the instrument test knowledge graph in step S2, and use logical knowledge reasoning technology to autonomously plan the instrument test process; then, a test instrument process autonomous rule base is constructed in step S3, and the instrument test planning process obtained in step S2 is intelligently judged based on this, achieving reliable planning of instrument test item test processes; then, a test instrument process autonomous rule base is constructed in step S3, and the instrument test planning process obtained in step S2 is intelligently judged based on this, achieving reliable planning of instrument test item test processes. These functional technologies are integrated into the autonomous test process planning software platform. After selecting the instrument model and test item, the platform automatically displays a knowledge map related to the test item and recommends a complete test process for the instrument test item. This enables autonomous planning of instrument test processes with high interpretability, promoting the development of autonomous and intelligent instrument testing.

[0035] In application: The present invention first obtains manuals of multiple types of instrument equipment, extracts and represents knowledge, and constructs knowledge triples of instrument performance detection as the data source of the instrument test process recommendation model; then, on this basis, it constructs an instrument detection knowledge graph to realize visual recommendation of instrument test processes, and at the same time establishes an autonomous expert rule base to generate a test process judgment scheme, intelligently judge the instrument test process, and improve the reliability of test process recommendation; finally, it establishes an instrument test system terminal platform, selects instrument models and test items on the platform side, and on the basis of the instrument test knowledge graph, utilizes knowledge reasoning technology and test process autonomous judgment technology to realize autonomous and accurate planning of instrument test processes.

[0036] This knowledge-based reasoning-based autonomous instrument test process planning method overcomes the shortcomings of existing test instrumentation, equipment, and methods, such as low efficiency and suboptimal interpretability of results. This method, applied to instrument performance testing, provides a reliable instrument test process planning solution with high interpretability, thereby improving both testing efficiency and the reliability of test results. The present invention also provides an application platform based on this method.

[0037] The above description shows the main features, basic principles, and advantages of the present invention. It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments or examples described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. The above embodiments or examples should therefore be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be encompassed within the present invention. Any reference numerals in the claims should not be construed as limiting the claims to which they relate.

[0038] In addition, it should be understood that although this specification is described in terms of implementation methods, not every implementation method contains only one independent technical solution. This narrative method of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation methods that can be understood by those skilled in the art.

Claims

1. A method for autonomous planning of instrument test processes based on knowledge reasoning, characterized by: The method The following steps are included: S1 - Instrument test process knowledge acquisition: Obtain user manuals of various types of test instruments, filter and extract knowledge text data as data sources; perform structured processing on the acquired knowledge text data, extract knowledge entities and entity relationships, and construct knowledge data of head entity, relationship, and tail entity triples for instrument testing; Using the extracted triple knowledge data, we build entity node sets and entity relationship sets, and store them in a JSON file in the form of a dictionary. S2 - Instrument test knowledge graph construction: Using the JavaScript-based visualization package D3.js, by reading the JSON file generated in step S1, the entity node data and entity relationship data constructed in step S1 are visualized in a graph, where each type of test instrument graph is displayed separately; the target information is searched for in the head entity and tail entity of the entity relationship data set, and a new relationship set is established after matching. Then, based on the head entity and tail entity in the newly established relationship set, a corresponding entity node set is constructed; using logical knowledge reasoning methods, the test process information of the target instrument test item is extracted and inferred from all the information; Using the knowledge reasoning rule framework, test process nodes are extracted and matched in the newly constructed entity relationship dataset containing all the information of the query target, and the instrument test process plan is generated through test process reasoning; S3- Intelligent judgment of test process based on autonomous rules: Establish an autonomous rule base for test instrument process. The rule items in the rule base are judged one by one according to the order of the instrument test process plan generated in step S2 until all rules are exhausted. The confidence of the overall instrument test process is calculated according to the following formula (1): In the above formula, J(i) represents the confidence of the overall planning process of test item i; s i Represents step x in test item i i ; n is the number of process steps in the process sequence of test item i; if the confidence is greater than the preset threshold, it is determined that the instrument test process planning is adopted.

2. The method for autonomous planning of instrument test processes based on knowledge reasoning according to claim 1 is characterized by: The knowledge text data described in step S1 includes text data of instrument models and various performance indicators, detection process methods, and fault detection methods.

3. The method for autonomous planning of instrument test processes based on knowledge reasoning according to claim 2 is characterized by: The triplet knowledge data described in step S1 includes head entity, relationship, and tail entity data, wherein the head entity and tail entity data correspond to instrument detection parameters; and the relationship data corresponds to the specific relationship or attributes between the entity data.

4. The method for autonomous planning of instrument test processes based on knowledge reasoning according to claim 3 is characterized by: In the dictionary storage described in step S1, the dictionary keys include head entity, tail entity, relationship, and key value length, and the dictionary values ​​are the head entity name, tail entity name, relationship name, and length value corresponding to the above keys.

5. The method for autonomous planning of instrument test processes based on knowledge reasoning according to claim 4 is characterized by: The confidence level in step S3 is used to determine whether to adopt the instrument test process plan output in step S2. If the confidence level is less than a threshold, the instrument test process plan is discarded and the instrument test is performed using a traditional manual method.

6. A knowledge-based reasoning-based autonomous instrument test process planning platform, characterized by: The platform includes an instrument model selection function module, an instrument test item selection function module, an instrument test knowledge graph display function module, and an instrument test process planning recommendation function module, which is used to implement steps S1 to S3 in the knowledge reasoning-based instrument test process autonomous planning method described in any one of claims 1 to 4, and finally output the generated instrument test process plan or use traditional manual methods to perform instrument test judgment results.

Images