Information query system and information query method

Abstract

The invention provides an information query system and an information query method. The information query system comprises a receiving unit, a calculation unit and an output unit. The receiving unit is used for receiving a query demand, and the query demand has a query value. The calculation unit is used for selecting a plurality of data strings conforming to the query value from historical data, each of the plurality of data strings comprises a first feature value and a second feature value, and the first feature value is related to the query value. The output unit is used for outputting at least one second characteristic value and a ratio of the at least one second characteristic value.

Description

Technical Field

[0001] This invention relates to an information query system and method. More specifically, this invention relates to an information query system and method capable of receiving query requests and correspondingly outputting feature values ​​and percentage values. Background Technology

[0002] In the field of knowledge accumulation and sharing, the accumulation and transfer of practical experience and past knowledge are crucial, yet also extremely difficult. For example, on a high-tech factory production line, when a machine displays an error code or makes unusual noises, it's often necessary to consult senior personnel to confirm the problem and resolve it. However, it's not always possible to contact senior personnel, and knowledge can be lost due to their departure. Therefore, managers frequently require senior personnel to document and retain the problem-solving process and related knowledge for easy reference and / or learning by others. However, over time, the number of documents written by senior personnel becomes enormous, making searching difficult. Furthermore, documents written by different personnel often vary in format, problem description, and completeness, further complicating the search. Therefore, even when knowledge searching is necessary, finding the correct answer from a large number of documents may not be possible, or it may take a very long time. A suitable solution to address these challenges remains lacking in this field. Summary of the Invention

[0003] The purpose of this invention is to provide an information query system and an information query method.

[0004] This invention provides an information query system, including a receiving unit, a calculation unit, and an output unit. The receiving unit receives a query request, which has a query value. The calculation unit selects a plurality of data strings from historical data that match the query value. Each of the plurality of data strings includes a first feature value and a second feature value, wherein the first feature value is related to the query value. The output unit outputs at least one second feature value and a percentage of the at least one second feature value.

[0005] This invention provides an information query method. The information query method is used in an information query system, which includes a receiving unit, a calculation unit, and an output unit. The information query method includes the following steps: The receiving unit receives a query request, which has a query value. The calculation unit selects a plurality of data strings from historical data that match the query value. Each of the plurality of data strings includes a first feature value and a second feature value, wherein the first feature value is related to the query value. The calculation unit generates at least one percentage value based on at least one first feature value, at least one second feature value, and the plurality of data strings. The output unit outputs the at least one percentage value and the at least one second feature value corresponding to the at least one percentage value. Attached Figure Description

[0006] Figure 1 This is a schematic diagram of the information query system in the embodiment.

[0007] Figure 2 For use Figure 1 The information query system provides a step-by-step guide to performing a query.

[0008] Figure 3 In the example, Figure 1 A visual diagram showing the second feature value and its corresponding percentage value output by the information query system.

[0009] Figure 4 In another embodiment, Figure 1 A visual diagram showing the second feature value and its corresponding percentage value output by the information query system.

[0010] Figure 5 For use Figure 1 The flowchart shows the information query method of the information query system.

[0011] Explanation of reference numerals in the attached diagram: 100 - Information query system; 110 - Receiving unit; 120 - Calculation unit; 130 - Output unit; 140 - Display unit; 105 - Input unit; 145 - Storage unit; 125 - Network unit; 155 - Cloud device; Qin - Query request; R - Query result; H - Historical data; S1, S4, S5, S6, S7 - Operation; D1, D2 - Database; C1, C2, C3, C11, C12, C13, C31, C32, C33 - Reason; K2, K3 - Buttons; 500 - Information query method; 510, 520, 530, 540 - Steps. Detailed Implementation

[0012] This invention can be described as follows. To explain this invention, various specific details and embodiments will be mentioned to enable its understanding. Specific elements and arrangements mentioned are used to clearly describe the invention. However, the exemplary embodiments in this invention are merely illustrative, and the concepts of this invention can be embodied in various reasonable embodiments and are not limited to the exemplary embodiments. Furthermore, in the drawings of different embodiments, similar and / or corresponding reference numerals may be used to indicate similar and / or corresponding elements, thereby clearly describing the invention. However, the use of similar and / or corresponding reference numerals in the drawings of different embodiments does not indicate a correlation between embodiments.

[0013] Certain terms are used throughout the description and the following scope of claims to refer to specific elements. As will be understood by those skilled in the art, electronic device manufacturers may use different names to refer to elements. This invention is not intended to distinguish elements with different names rather than different functions. In the following description and within the scope of claims, the terms “comprising,” “including,” and “having” are used in an open-ended manner and should therefore be interpreted as meaning “including but not limited to…”. Thus, when the terms “comprising,” “including,” and / or “having” are used in the description of this invention, it indicates the presence of corresponding features, areas, steps, operations, and / or elements, but is not limited to the presence of one or more corresponding features, areas, steps, operations, and / or components.

[0014] It should be understood that although the terms first, second, third, etc., in this invention can be used to describe various elements, components, regions, layers, parts, and / or components, these elements, components, regions, layers, parts, and / or components should not be limited by these terms. These terms are only used to distinguish one element, component, region, layer, part, or component from another element, component, region, layer, part, or component. Therefore, without departing from the teachings of this invention, the first element, component, region, layer, part, or component discussed below may be referred to as the second element, component, region, layer, part, or component.

[0015] It should be understood that, in this invention, the description of exemplary embodiments is intended to be read in conjunction with the accompanying drawings, which may be considered an integral part of the entire written description. The drawings are not drawn to scale. Furthermore, for the sake of simplicity, structures and apparatus are presented schematically.

[0016] Unless otherwise defined, all technical and scientific terms used in this invention may have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should be understood that, unless otherwise defined, in various cases, terms as defined in commonly used dictionaries may be interpreted as having a meaning consistent with the relevant skill and context of this invention, and should not be interpreted in an idealized or overly formal manner.

[0017] In this invention, when referring to multiple objects, if connected by "and / or", it means each of the multiple objects and any combination thereof. For example, when referring to "A, B and / or C", it includes any one of "A", "B", "C", "A and B", "A and C", "B and C", and "A, B and C".

[0018] Furthermore, in some embodiments of the present invention, unless otherwise explicitly stated, terms such as "connection," "interconnection," and "coupling" refer to the relationship in which structures are directly or indirectly fixed or connected to each other through intermediate structures or elements, as well as movable or rigid attachments or relationships.

[0019] The electronic device of this invention may include, but is not limited to, a display device, an antenna device, a sensing device, a light-emitting device, a touch display, a curved display, or a free-shape display. The electronic device may include bendable or flexible electronic devices. The electronic device may include, for example, electronic components, liquid crystal, light-emitting diodes (LEDs), quantum dots (QDs), fluorescence, phosphorescence, other suitable display media, or combinations of the above materials, but is not limited thereto. Electronic components may include passive and active components, such as capacitors, resistors, inductors, diodes, transistors, etc. Diodes may include light-emitting diodes or photodiodes. Light-emitting diodes may include, for example, organic light-emitting diodes (OLEDs), mini LEDs, micro LEDs, or quantum dot LEDs (including QLEDs, QDLEDs), or other suitable materials, or combinations thereof, but are not limited thereto. The display device may include, for example, a video wall display device, but is not limited thereto. The antenna device may be, for example, a liquid crystal antenna, but is not limited thereto. The antenna device may include, for example, an antenna splicing device, but is not limited thereto. It should be noted that the electronic device may be any of the aforementioned arrangements and combinations, but is not limited thereto. Furthermore, the electronic device may be rectangular, circular, polygonal, have curved edges, or other suitable shapes. The electronic device may have peripheral systems such as a drive system, control system, and light source system to support the display device, antenna device, or splicing device, but the present invention is not limited thereto. The sensing device may include a camera, an infrared sensor, or a fingerprint sensor, etc., and the present invention is not limited thereto. In some embodiments, the sensing device may also include a flash, an infrared (IR) light source, other sensors, electronic components, or combinations thereof, but is not limited thereto.

[0020] It should be noted that the technical features in the different embodiments described below may be replaced, reorganized or combined with each other to form another embodiment without departing from the spirit of the invention.

[0021] Figure 1This is a schematic diagram of the information query system 100 in an embodiment. The information query system 100 may include a receiving unit 110, a calculation unit 120, and an output unit 130. The receiving unit 110 can be used to receive a query request Qin, which may have a query value. The calculation unit 120 can be used to select a plurality of data strings from historical data H that match the query value of the query request Qin. Each of the plurality of data strings may include a first feature value and a second feature value. The calculation unit 120 can select the plurality of data strings that match the query value of the query request Qin using an information retrieval language model method. The query request Qin may include a text string to describe the query problem. For example, a user may input a text string to describe a problem encountered by a machine or factory during production, such as an error code of the machine, or a description of abnormal noises emitted by the machine in natural language, but is not limited to this. The query value may include numbers, text, words, or combinations thereof, but is not limited to this. Historical data may include a plurality of data strings, each of which may be a document or a text string in historical data H, used to describe a problem that occurred in a machine or factory during the production of electronic devices, the abnormal behavior of the machine at the time the problem occurred, and the methods and / or steps to solve the problem, but is not limited thereto. Each data string may include a first feature value and a second feature value, which may include a text string. For example, the first feature value may be a text string describing the problem, and the second feature value may be a text string describing the cause of the problem or a text string describing the methods and / or steps to solve the problem. For example, the first feature value may be a problem encountered by the machine or factory on the production line, which may be a defect symptom discovered by the user in the production process. The second feature value may be the real root cause of the problem described in historical data H. Output unit 130 may be used to output query result R, which may include at least one of the second feature values ​​and the percentage of the second feature value.

[0022] For example, a user can input an anomaly in an engineering problem using a query request (Qin). For instance, a user could submit a query request (Qin) about a vertical line (V-line) anomaly occurring during the manufacturing of a display panel. The calculation unit 120 can then compare and / or retrieve a first feature value from historical data H based on keywords (e.g., V-line). If the first feature value has a high correlation with the query request (Qin), it indicates that the first feature value is relevant to the query value of the query request (Qin). At least one second feature value and its corresponding percentage value from the data string matching the query request (Qin) can be returned within a short time (e.g., within 10 seconds, but not limited to this). For example, the output unit 130 can output three root causes corresponding to the vertical line anomaly problem and their percentage values, which could be electrostatic discharge (ESD) 35%, thin-film transistor (TFT) defects 40%, and source chip bonding defects 25%. The percentage values ​​corresponding to these multiple root causes can be summed to 100%. Therefore, after users input their engineering problems into the query system (Qin), they can quickly obtain multiple root causes and their corresponding percentages, which helps to prompt users and speed up debugging. For example, in the past, when engineering problems occurred, it often took weeks, sometimes even months, to find the root cause and implement preventative and improvement measures. However, by using the information query system 100, the accumulated experience from historical data H can be effectively applied, shortening the debugging time to within days, a day, or even minutes to find the possible root causes for prevention and / or improvement.

[0023] According to an embodiment, the second feature value and its corresponding proportion can be the quotient of the first value divided by the second value, which can be calculated based on conditional probability. The first value divided by the second value can be expressed as P(real root cause|defect symptom) = P(defect symptom&real root cause) / P(defect symptom). Here, the first value (P(defect symptom&real root cause) above) can correspond to the maximum number of data strings with the same second feature value among the plurality of data strings corresponding to the first feature value in historical data H. The second value (P(defect symptom) above) can correspond to the number of data strings containing the first feature value in historical data H. In this way, the second feature value with the highest probability (e.g., the "real root cause" of the problem) can be output. For example, the most probable "real root cause" can be provided to help users debug.

[0024] In another embodiment, the second feature value and its corresponding percentage can be the quotient of the first value divided by the second value. This can be calculated based on conditional probability, as described below. The first value divided by the second value can be expressed as P(real root cause|defect symptom) = P(defect symptom&real root cause) / P(defect symptom). Here, the first value (P(defect symptom&real root cause) above) can correspond to the number of data strings in the historical data H containing the first feature value, each with a different second feature value. The second value (P(defect symptom) above) can correspond to the number of data strings in the historical data H containing the first feature value. In this way, all possible second feature values ​​(e.g., the "real root cause" of the problem) and their corresponding percentages can be output. For example, multiple "real root causes" and their corresponding percentages can be provided to help users debug.

[0025] The calculations mentioned here, and how the percentage values ​​are generated, will be discussed later. Figure 2 The instructions will provide examples and explain step by step how to perform detailed calculations.

[0026] Optionally, such as Figure 1As shown, the receiving unit 110 can receive the query request Qin input by the user through the input unit 105. For example, the input unit 105 may include a microphone, keyboard, handwriting tablet, selection buttons, etc., but the present invention is not limited thereto. The display unit 140 can receive the query result R to display the aforementioned second characteristic value and its percentage value, such as the cause and corresponding percentage value of problems such as "electrostatic discharge 35%, thin film transistor defects 40%, and source chip bonding defects 25%" mentioned in the present invention. For example, the display unit 140 may include a display, related control circuits, software, and / or hardware, but the present invention is not limited thereto. The display unit 140 may include a general display, OLED display, microLED display, flexible display, etc., but the present invention is not limited thereto. In one embodiment, the information query system 100 may further include a network unit 125 and / or a storage unit 145. Historical data H may be stored in a cloud device 155, and the computing unit 120 may receive historical data H from the cloud device 155 through the network unit 125. For example, network unit 125 may include a network interface, a network modem, and / or a network card, etc., but the present invention is not limited thereto. Optionally, historical data H may be stored in cloud device 155. For example, cloud device 155 may be a cloud hard drive located in the cloud, and the path between cloud device 155 and network unit 125 may include a wired path and / or a wireless path. During the calculation and data processing of information retrieval system 100, all data may be stored in storage unit 145 for access. Storage unit 145 may include buffer memory, main memory, dynamic random access memory (DRAM), and / or static random access memory (SRAM), but the present invention is not limited thereto.

[0027] Figure 2 For use Figure 1 The diagram illustrates the steps for performing a query on the information query system 100. Figure 2 In step S1, the user can describe the problem encountered and input the query request Qin into the information query system 100.

[0028] In step S2, similar data can be found in historical data H based on the query value of the query request Qin, to generate multiple data strings. Historical data H may include past experience and / or cases, and may be provided by database D1.

[0029] In step S3, a second value corresponding to the first feature value, and a first value corresponding to both the first and second feature values, can be calculated. For example, the first feature value may include the "symptom of the defect" in the user-input question, and the second feature value may include the "root cause" corresponding to the symptom of the defect. The first and second feature values ​​can be provided by database D2. Databases D1 and D2 can be set simultaneously. Figure 1In the cloud device 155 and / or storage unit 145, or respectively disposed in Figure 1 The present invention is not limited thereto, but can be found in cloud device 155 and / or storage unit 145.

[0030] In step S4, conditional probability calculations can be performed based on the first and second values ​​to generate a percentage value corresponding to the second feature value (e.g., the "true root cause" of the problem).

[0031] In step S5, at least one second feature value and its corresponding percentage value can be output.

[0032] The following are examples, such as Figure 1 and Figure 2 As shown, in step S1, the user can input the keyword "V-line" as the query requirement Qin. In step S2, the calculation unit 120 can select a plurality of data strings that match the query requirement Qin using the best matching method. For example, the best matching method may include the Okapi BM25 algorithm (also known as the BM25 algorithm), keyword search algorithm, embedding search algorithm, and / or ensemble search algorithm, etc.

[0033] For example, in step S2, when the user inputs "V-line", the BM25 algorithm can be used to find 20 files (i.e., 20 data strings) in historical data H. In step S3, based on a plurality of first feature values ​​(e.g., "defect symptoms") and a plurality of second feature values ​​(e.g., "root cause") in database D2, it can be determined that among the 20 data strings obtained in step S2, 10 contain the first feature value corresponding to the query requirement Qin, and 3 contain both the first and second feature values ​​corresponding to the query requirement Qin. In this example, the following first and second values ​​can be obtained:

[0034] P(defect symptom)=10 / 20=0.5;

[0035] P(defect symptom&real root cause)=3 / 20=0.15;

[0036] The second value is P(defect symptom), and the first value is P(defect symptom & real root cause). In step S4, conditional probability calculation can be performed, which can be expressed as follows:

[0037] P(real root cause|defect Symptom)=P(defect symptom&real root cause) / P(defect symptom);

[0038] In the example above, P(real root cause|defect Symptom) = P(defect Symptom&real root cause) / P(defect symptom) = 0.15 / 0.5 = 30%. Here, P(real root cause|defect Symptom) can be the aforementioned percentage value. Therefore, in step S5, the corresponding second characteristic value (e.g., the "real root cause" of the problem) and the percentage value can be output. For example, if the second characteristic value here is "source chip bonding defect," and the corresponding percentage value is "30%," the user will see the result "source chip bonding defect 30%" displayed in step S5. Figure 1 The display unit 140 can thus indicate the true root cause of the problem to the user, helping the user to troubleshoot.

[0039] Regarding information retrieval, the Okapi BM25 (Best Matching 25, BM25) algorithm mentioned earlier can be considered an improved version based on the Okapi TF-IDF algorithm. The BM25 algorithm can be used to estimate the file (hereinafter referred to as d) and the user query (hereinafter referred to as Q, which corresponds to the case here). Figure 1 The correlation between the query requirement (Qin) is suitable for handling long files and short queries. File d can correspond to... Figure 1 Historical data H. BM25 can calculate the relevance between file d and user query Q based on term frequency (TF) and inverse document frequency (IDF), and can also consider file length information.

[0040] BM25 score can be expressed as Here, qi can be the i-th word in the query, Wi can be the weight of word qi, and R(qi, d) can be the relevance score between word qi and file d. The weight Wi can be used to determine the relevance between a word and a file; for example, the IDF algorithm can be used. N can be the total number of files, and n(qi) can be the number of files containing the word qi.

[0041] The keyword search algorithm mentioned in this invention can use the BM25 algorithm to select relevant documents, and it is more effective for keywords in specific fields, such as names of people and structures. The embedding search algorithm can use an embedding model to embed the query and corpus into text, and use vector similarity for text matching, which can address the shortcomings of the BM25 algorithm in recalling similar keywords; for example, a vector database can be used. The ensemble search algorithm can combine the results of the BM25 algorithm and the embedding search, and use a re-ranking algorithm for final sorting, potentially achieving better results than individual recall algorithms.

[0042] In other embodiments, relevant data strings can be found through Language Model Information Retrieval (LMIR), but this invention is not limited thereto. Regarding Language Model Information Retrieval (LMIR), a language model can be used to calculate a relevance score between a document and a query. The most common formula used is Kullback-Leibler divergence to measure the similarity between a document and a query. The following is the KL divergence formula used in LMIR:

[0043] Suppose we have a query Q and a document D, where w represents the words in the document. These are represented by the probability distributions P(w|Q) and P(w|D), respectively. The relevance score between document D and query Q can be calculated using the KL divergence:

[0044]

[0045] Where P(w|Q) represents the probability of word w in query Q, and P(w|D) represents the probability of word w in document D. This formula means that for each word w in the query, the logarithm of the ratio of its probability in the query to its probability in the document is calculated, and then summed to obtain the relevance score.

[0046] The intuitive interpretation of the above formula is that it measures the difference between the words in the query and the words in the document, thereby assessing the relevance between the document and the query. Based on the calculated relevance score, documents can be ranked to provide the most relevant documents as search results.

[0047] Figure 3 and Figure 4 In this embodiment, a visual diagram of multiple second feature values ​​(e.g., the "true root cause" of the problem) and their corresponding percentage values ​​output by the information query system 100 is provided. Figure 3It can be a schematic diagram of a tree branch. Figure 4 This can be a list-style diagram. Optionally, Figure 3 and Figure 4 One output can be selected to the display unit (e.g.) Figure 1 (As shown) can be displayed to the user, or both can be output to the user for viewing. The user can set it according to their needs.

[0048] like Figures 1 to 3 As shown, when a user inputs a query request Qin, the information query system 100 can, based on the query value of Qin (e.g., keywords) and at least one first feature value and at least one second feature value of database D2, inform the user that the second feature value corresponding to the problem in the query request Qin (e.g., the "true root cause" of the problem) includes cause C1, cause C2, and cause C3. In other words, the problem in the query request Qin may be caused by cause C1, cause C2, and / or cause C3. The percentage values ​​corresponding to cause C1, cause C2, and cause C3 can be 10%, 10%, and 80%, respectively. Therefore, in this example, cause C3 is more likely to explain and / or resolve the query request Qin, but the user can still make their own judgment.

[0049] Furthermore, the information query system 100 can further analyze the deeper, true root causes of the defect symptoms corresponding to cause C1 and cause C3. For example... Figure 3 For example, the defect symptoms corresponding to cause C1 may be caused by causes C11, C12, and / or C13, with the percentages for causes C11, C12, and C13 being 5%, 80%, and 15%, respectively. The defect symptoms corresponding to cause C3 may be caused by causes C31, C32, and / or C33, with the percentages for causes C31, C32, and C33 being 60%, 30%, and 10%, respectively. Therefore, a tree-like diagram can provide users with more and deeper clues and hints to help them troubleshoot. Figure 3 As shown, each time the search moves down to the next level to find the true root cause, the percentage values ​​corresponding to each branch are added together to reach 100%.

[0050] Figure 3 For illustrative purposes only, according to an embodiment, Figure 3The query request Qin and each of the reasons C1, C2, C3, C11, C12, C13, C31, C32, and C33 may include at least one keyword or descriptive sentence to facilitate user reading. For example, reason C31 may list electrostatic discharge (ESD), reason C32 may list thin-film transistor (TFT) defects, and reason C33 may list liquid crystal (LCD) defects, etc., to help users troubleshoot. Figure 3 For example only, in different situations, a dendrite can have more branches to provide more possible causes of the problem.

[0051] Figure 4 A list is provided, which sorts the defect symptoms and the root causes according to the percentage of the actual root cause, making it easier for users to view. Figure 4 The listed defect symptoms can be the relevant defect symptoms that the calculation unit 120 finds in historical data H according to the query requirements Qin. Figure 4 In the study, the correlation coefficient of the true root cause C31 (0.48) is considered to be... Figure 3 The product of the percentage corresponding to cause C3 (80%) and the percentage corresponding to cause C31 (60%). Figure 4 In the middle, the correlation of the true root cause C32 (0.24) can be considered as... Figure 3 The product of the percentage corresponding to cause C3 (80%) and the percentage corresponding to cause C32 (30%). Figure 4 In the study, the correlation coefficient of the true root cause C33 (0.08) is considered to be... Figure 3 The product of the percentage corresponding to reason C3 (80%) and the percentage corresponding to reason C33 (10%). Similarly, the various true root causes of the query request Qin in historical file H can be sorted and listed according to their relevance for user viewing, thus aiding in troubleshooting. Figure 4 In the example, reason C31 is the true root cause ranked first, but this is only for reference and users can make their own judgment.

[0052] If historical file H provides relevant information, Figure 4 The table can be set up with a "Suggested Prescription" field, and virtual buttons K2 and K3 can be set up for users to click to get relevant information on how to deal with the problem. Figure 4 The names and layout of each field are provided as examples. Users can modify the arrangement and names of the fields according to their needs.

[0053] Figure 5 For use Figure 1 The flowchart of the information query method 500 of the information query system 100. (For example...) Figure 1 and Figure 5 As shown, information retrieval method 500 may include the following steps:

[0054] Step 510: The receiving unit 110 receives the query request Qin, which has a query value;

[0055] Step 520: Calculation unit 120 selects a plurality of data strings that match the query value from historical data H;

[0056] Step 530: Calculation unit 120 generates at least one proportion value based on at least one first feature value, at least one second feature value, and the plurality of data strings; and

[0057] Step 540: The output unit 130 outputs the at least one percentage value and a set of second feature values ​​corresponding to the at least one percentage value.

[0058] In step 520, an appropriate algorithm can be used to select a plurality of data strings, and the plurality of data strings can be a plurality of documents in the historical data H. For example, an appropriate algorithm may include the Okapi BM25 algorithm or other appropriate algorithms. The at least one first feature value and at least one second feature value described in step 530 can be stored in a glossary format. Figure 2 Database D2, and from Figure 2 The database D2 is read. For example, the first feature value can be a defect symptom of the production line and the product, and the second feature value can be the true root cause of the defect symptom. In step 530, the conditional probability calculation described above can be performed to generate a ratio corresponding to each second feature value. In step 540, a set of second feature values ​​(e.g., the true root cause) and a corresponding set of ratio values ​​can be output for the user to view, so that the user can debug. In step 540, the database D2 can be used. Figure 3 and / or Figure 4 In this way, the second feature value (e.g., the true root cause) and the corresponding percentage value are output for easy reference by users.

[0059] In summary, by using the information query system 100 and information query method 500 provided in this embodiment, users can obtain information such as [example information] within minutes or even seconds after inputting their query request (Qin). Figure 3 and / or Figure 4 The results not only reveal the true root cause of the problem but also show the corresponding percentage. Therefore, it saves a significant amount of time searching through historical files and provides quick and effective clues for debugging, offering significant assistance to various knowledge fields such as industrial manufacturing, education, and academia.

[0060] This invention also provides a computer-readable storage medium having a computer program stored thereon, the computer program being used to cause a computer to execute the information query method described in the embodiments above.

[0061] This invention also provides a computer non-volatile readable storage medium storing one or more program modules. When the one or more program modules are used in a device, the device can execute instructions containing the steps of any one of the embodiments described above.

[0062] The aforementioned computer-readable storage media may be, for example, (but not limited to) electrical, magnetic, optical, electromagnetic, infrared, or semiconductor devices or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), optical fiber, read-only optical disk (CD-ROM), optical storage devices, magnetic storage devices, or suitable combinations thereof.

[0063] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An information query system, characterized in that, include: A receiving unit is used to receive a query request, wherein the query request has a query value; A calculation unit is configured to select a plurality of data strings from historical data that match the query value, each of the plurality of data strings including a first feature value and a second feature value, wherein the first feature value is related to the query value; and An output unit is used to output at least one second feature value and a percentage of the at least one second feature value.

2. The information query system as described in claim 1, characterized in that, The percentage of the at least one second feature value is a quotient value generated by dividing a first value by a second value, wherein the second value corresponds to the number of data strings containing the first feature value among the plurality of data strings, and the first value corresponds to the maximum number of data strings containing the first feature value that have the same second feature value among the plurality of data strings.

3. The information query system as described in claim 1, characterized in that, The proportion of at least one second feature value is a plurality of quotients generated by dividing a plurality of first values ​​by a second value, wherein the second value corresponds to the number of data strings containing the first feature value in the plurality of data strings, and the plurality of first values ​​respectively correspond to the number of data strings containing the first feature value that have each different second feature value.

4. The information query system as described in claim 1, characterized in that, The query request is transmitted to the receiving unit through an input unit.

5. The information query system as described in claim 1, characterized in that, The percentage of at least one of the second feature values ​​is presented through a display unit.

6. The information query system as described in claim 1, characterized in that, The historical data is stored in a cloud device.

7. The information query system as described in claim 6, characterized in that, The information query system receives the historical data through a network unit.

8. The information query system as described in claim 1, characterized in that, The calculation unit selects the plurality of data strings that match the query value using the best matching method.

9. The information query system as described in claim 1, characterized in that, The computing unit selects the plurality of data strings that match the query value using an information retrieval language model.

10. An information retrieval method, characterized in that, The information query method is used in an information query system, which includes a receiving unit, a calculation unit, and an output unit, and the information query method includes: The receiving unit receives a query request, the query request having a query value; The calculation unit selects a plurality of data strings that match the query value from historical data. Each of the plurality of data strings includes a first feature value and a second feature value, wherein the first feature value is related to the query value. The calculation unit generates at least one proportion value based on at least one first feature value, at least one second feature value, and the plurality of data strings; and The output unit outputs the at least one percentage value and the at least one second feature value corresponding to the at least one percentage value.

Images