A fast retrieval method and system for large-scale intelligence data based on large models

Abstract

The invention discloses a method and system for quickly retrieving large-scale intelligence data based on a large model. The method comprises: obtaining a query sentence given by a user and document information of a satellite data document, wherein the query sentence comprises: a plurality of terms and the frequency of occurrence of the terms in the query sentence, and the document information comprises: the length of the satellite data document and the average length of the satellite data document; setting a retrieval relevance evaluation model, and calculating a relevance score for evaluating the query sentence given by the user and the satellite data document according to the query sentence and the document information; setting a relevance threshold, and if the relevance score is greater than or equal to the relevance threshold, displaying the satellite data document corresponding to the highest relevance score to the user, otherwise prompting that the query sentence has been retrieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of information retrieval, and more specifically, relates to a fast retrieval method and system for large-scale intelligence data based on a large model. Background Art

[0002] Information retrieval technology plays a key role in many fields and applications. Here are some of the main ones:

[0003] 1. Improve efficiency

[0004] Information retrieval technology can quickly find the required information in a large amount of data, greatly improving work efficiency. For example, a search engine can provide web pages related to a query within seconds.

[0005] 2. Data Management

[0006] Information retrieval technology helps organize and manage large amounts of data, allowing users to easily store, retrieve, and analyze information. For example, companies can use information retrieval systems to manage internal documents and emails.

[0007] 3. Knowledge Discovery

[0008] Through effective information retrieval technology, hidden knowledge and patterns can be discovered from massive data. For example, in the medical field, researchers can search medical literature to find new treatments for diseases.

[0009] 4. Information filtering

[0010] Information retrieval technology can filter out irrelevant information and help users focus on important and relevant data. For example, recommendation systems can provide personalized content recommendations based on users' interests.

[0011] However, there is no technical solution in the prior art that can accurately retrieve information. Summary of the invention

[0012] In order to solve the above technical problems, the present invention proposes a rapid retrieval method for large-scale intelligence data based on a large model, wherein the intelligence data is a satellite data file, including:

[0013] Acquire a query sentence given by a user and document information of the satellite data document, wherein the query sentence includes: a plurality of terms and the frequency of occurrence of the terms in the query sentence, and the document information includes: the length of the satellite data document and the average length of the satellite data document;

[0014] Setting a retrieval relevance evaluation model, and calculating a relevance score for evaluating the query sentence given by the user and the satellite data document according to the query sentence and the document information;

[0015] A relevance threshold is set, and if the relevance score is greater than or equal to the relevance threshold, the satellite data document corresponding to the highest relevance score is displayed to the user, otherwise a prompt is given that the query sentence is retrieved.

[0016] Furthermore, the retrieval relevance evaluation model includes:

[0017] ,

[0018] in, To evaluate the query sentence given by the user and satellite data files The correlation score between For query sentence The Terms The inverse document frequency of For query sentence The term, For query sentence The Terms In the query sentence The frequency in is the first adjustment factor for correlation, is the second adjustment factor for correlation, Satellite data files Length, Satellite data files The average length of For the relevant A third adjustment factor, For query sentence and satellite data files The spatial similarity between For query sentence and satellite data files The time similarity between them.

[0019] Further, query the sentence and satellite data files The spatial similarity between include:

[0020] ,

[0021] in, is the first adjustment factor of spatial similarity, Satellite data files No. The spatial feature vectors, is the transpose of the matrix, is the covariance matrix, is the second adjustment factor of spatial similarity, For time.

[0022] Further, query the sentence and satellite data files The time similarity between include:

[0023] ,

[0024] in, is the first adjustment factor of temporal similarity, For query sentence timestamp, Satellite data files The timestamp of the spatial feature vector, is the second adjustment factor of time similarity.

[0025] Furthermore, all adjustment factors are fitted by gradient descent method.

[0026] The present invention also proposes a rapid retrieval system for large-scale intelligence data based on a large model, comprising:

[0027] An information acquisition module is used to acquire a query sentence given by a user and document information of the satellite data document, wherein the query sentence includes: a plurality of terms and the frequency of occurrence of the terms in the query sentence, and the document information includes: the length of the satellite data document and the average length of the satellite data document;

[0028] Setting a model module, used to set a retrieval relevance evaluation model, and calculating a relevance score for evaluating the query sentence given by the user and the satellite data document according to the query sentence and the document information;

[0029] The retrieval module is used to set a relevance threshold. If the relevance score is greater than or equal to the relevance threshold, the satellite data document corresponding to the highest relevance score is displayed to the user; otherwise, a prompt is given that the query sentence is retrieved.

[0030] Furthermore, the retrieval relevance evaluation model includes:

[0031] ,

[0032] in, To evaluate the query sentence given by the user and satellite data files The correlation score between For query sentence The Terms The inverse document frequency of For query sentence The term, For query sentence The Terms In the query sentence The frequency in is the first adjustment factor for correlation, is the second adjustment factor for correlation, Satellite data files Length, Satellite data files The average length of For the relevant A third adjustment factor, For query sentence and satellite data files The spatial similarity between For query sentence and satellite data files The time similarity between them.

[0033] Further, query the sentence and satellite data files The spatial similarity between include:

[0034] ,

[0035] in, is the first adjustment factor of spatial similarity, Satellite data files No. The spatial feature vectors, is the transpose of the matrix, is the covariance matrix, is the second adjustment factor of spatial similarity, For time.

[0036] Further, query the sentence and satellite data files The time similarity between include:

[0037] ,

[0038] in, is the first adjustment factor of temporal similarity, For query sentence timestamp, Satellite data files The timestamp of the spatial feature vector, is the second adjustment factor of time similarity.

[0039] Furthermore, all adjustment factors are fitted by gradient descent method.

[0040] In general, the above technical solution conceived by the present invention has the following beneficial effects compared with the prior art:

[0041] The invention sets a retrieval relevance evaluation model, and calculates a relevance score for evaluating the query sentence given by the user and the satellite data document based on the query sentence and the document information; sets a relevance threshold, and if the relevance score is greater than or equal to the relevance threshold, displays the satellite data document corresponding to the highest relevance score to the user, otherwise it prompts that the query sentence has been retrieved. Through the above technical solution, the invention can perform accurate and fast information retrieval of satellite intelligence data. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flow chart of the method of embodiment 1 of the present invention;

[0043] Figure 2 It is a structural diagram of the system of embodiment 2 of the present invention. DETAILED DESCRIPTION

[0044] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0045] The method provided by the present invention can be implemented in the following terminal environment, and the terminal may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, and the instruction is loaded and executed by the processor to implement the method described in the following embodiment.

[0046] The processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts in the entire terminal, and executes various functions of the terminal and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and calling data stored in the storage medium.

[0047] The storage medium may include a random access memory (RAM) or a read-only memory (ROM). The storage medium may be used to store instructions, programs, codes, code sets or instructions.

[0048] The display screen is used to display the user interface of each application.

[0049] In addition, those skilled in the art can understand that the structure of the above terminal does not constitute a limitation on the terminal, and the terminal may include more or fewer components, or combine certain components, or arrange the components differently. For example, the terminal also includes components such as a radio frequency circuit, an input unit, a sensor, an audio circuit, and a power supply, which will not be described in detail here.

[0050] Example 1

[0051] like Figure 1 As shown, an embodiment of the present invention provides a method for quickly retrieving large-scale intelligence data based on a large model, wherein the intelligence data is a satellite data document, including:

[0052] Step 101, obtaining a query sentence given by a user and document information of the satellite data document, wherein the query sentence includes: a plurality of terms and the frequency of occurrence of the terms in the query sentence, and the document information includes: the length of the satellite data document and the average length of the satellite data document;

[0053] Step 102, setting a retrieval relevance evaluation model, and calculating a relevance score for evaluating the query sentence given by the user and the satellite data document according to the query sentence and the document information;

[0054] Specifically, the retrieval relevance evaluation model includes:

[0055] ,

[0056] in, To evaluate the query sentence given by the user and satellite data files The correlation score between For query sentence The Terms The inverse document frequency of For query sentence The term, For query sentence The Terms In the query sentence The frequency in is the first adjustment factor for correlation, is the second adjustment factor for correlation, Satellite data files Length, Satellite data files The average length of For the relevant A third adjustment factor, For query sentence and satellite data files The spatial similarity between For query sentence and satellite data files The time similarity between them.

[0057] Specifically, query sentence and satellite data files The spatial similarity between include:

[0058] ,

[0059] in, is the first adjustment factor of spatial similarity, Satellite data files No. The spatial feature vectors, is the transpose of the matrix, is the covariance matrix, is the second adjustment factor of spatial similarity, For time.

[0060] Specifically, query sentence and satellite data files The time similarity between include:

[0061] ,

[0062] in, is the first adjustment factor of temporal similarity, For query sentence timestamp, Satellite data files The timestamp of the spatial feature vector, is the second adjustment factor of time similarity.

[0063] Specifically, all adjustment factors are fitted by gradient descent method.

[0064] Step 103, setting a relevance threshold, if the relevance score is greater than or equal to the relevance threshold, displaying the satellite data document corresponding to the highest relevance score to the user, otherwise prompting that the query sentence has been retrieved.

[0065] Example 2

[0066] like Figure 2 As shown, the embodiment of the present invention also provides a rapid retrieval system for large-scale intelligence data based on a large model, wherein the intelligence data is a satellite data file, including:

[0067] An information acquisition module is used to acquire a query sentence given by a user and document information of the satellite data document, wherein the query sentence includes: a plurality of terms and the frequency of occurrence of the terms in the query sentence, and the document information includes: the length of the satellite data document and the average length of the satellite data document;

[0068] Setting a model module, used to set a retrieval relevance evaluation model, and calculating a relevance score for evaluating the query sentence given by the user and the satellite data document according to the query sentence and the document information;

[0069] Specifically, the retrieval relevance evaluation model includes:

[0070] ,

[0071] in, To evaluate the query sentence given by the user and satellite data files The correlation score between For query sentence The Terms The inverse document frequency of For query sentence The term, For query sentence The Terms In the query sentence The frequency in is the first adjustment factor for correlation, is the second adjustment factor for correlation, Satellite data files Length, Satellite data files The average length of For the relevant A third adjustment factor, For query sentence and satellite data files The spatial similarity between For query sentence and satellite data files The time similarity between them.

[0072] Specifically, query sentence and satellite data files The spatial similarity between include:

[0073] ,

[0074] in, is the first adjustment factor of spatial similarity, Satellite data files No. The spatial feature vectors, is the transpose of the matrix, is the covariance matrix, is the second adjustment factor of spatial similarity, For time.

[0075] Specifically, query sentence and satellite data files The time similarity between include:

[0076] ,

[0077] in, is the first adjustment factor of temporal similarity, For query sentence timestamp, Satellite data files The timestamp of the spatial feature vector, is the second adjustment factor of time similarity.

[0078] Specifically, all adjustment factors are fitted by gradient descent method.

[0079] The retrieval module is used to set a relevance threshold. If the relevance score is greater than or equal to the relevance threshold, the satellite data document corresponding to the highest relevance score is displayed to the user; otherwise, a prompt is given that the query sentence is retrieved.

[0080] Example 3

[0081] An embodiment of the present invention further proposes a storage medium storing a plurality of instructions, wherein the instructions are used to implement the method for rapid retrieval of large-scale intelligence data based on a large model.

[0082] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0083] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps: Step 101, obtaining a query sentence given by a user and document information of the satellite data document, wherein the query sentence includes: a plurality of terms and the frequency of occurrence of the terms in the query sentence, and the document information includes: the length of the satellite data document and the average length of the satellite data document;

[0084] Step 102, setting a retrieval relevance evaluation model, and calculating a relevance score for evaluating the query sentence given by the user and the satellite data document according to the query sentence and the document information;

[0085] Specifically, the retrieval relevance evaluation model includes:

[0086] ,

[0087] in, To evaluate the query sentence given by the user and satellite data files The correlation score between For query sentence The Terms The inverse document frequency of For query sentence The term, For query sentence The Terms In the query sentence The frequency in is the first adjustment factor for correlation, is the second adjustment factor for correlation, Satellite data files Length, Satellite data files The average length of For the relevant A third adjustment factor, For query sentence and satellite data files The spatial similarity between For query sentence and satellite data files The time similarity between them.

[0088] Specifically, query sentence and satellite data files The spatial similarity between include:

[0089] ,

[0090] in, is the first adjustment factor of spatial similarity, Satellite data files No. The spatial feature vectors, is the transpose of the matrix, is the covariance matrix, is the second adjustment factor of spatial similarity, For time.

[0091] Specifically, query sentence and satellite data files The time similarity between include:

[0092] ,

[0093] in, is the first adjustment factor of temporal similarity, For query sentence timestamp, Satellite data files The timestamp of the spatial feature vector, is the second adjustment factor of time similarity.

[0094] Specifically, all adjustment factors are fitted by gradient descent method.

[0095] Step 103, setting a relevance threshold, if the relevance score is greater than or equal to the relevance threshold, displaying the satellite data document corresponding to the highest relevance score to the user, otherwise prompting that the query sentence has been retrieved.

[0096] Example 4

[0097] An embodiment of the present invention also proposes an electronic device, including a processor and a storage medium connected to the processor, wherein the storage medium stores a plurality of instructions, and the instructions can be loaded and executed by the processor so that the processor can execute the method for rapid retrieval of large-scale intelligence data based on a large model.

[0098] Specifically, the electronic device of this embodiment may be a computer terminal, and the computer terminal may include: one or more processors, and a storage medium.

[0099] Among them, the storage medium can be used to store software programs and modules, such as a fast retrieval method for large-scale intelligence data based on a large model in an embodiment of the present invention, corresponding program instructions / modules, and the processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium, that is, realizing the above-mentioned fast retrieval method for large-scale intelligence data based on a large model. The storage medium may include a high-speed random storage medium, and may also include a non-volatile storage medium, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include a storage medium remotely arranged relative to the processor, and these remote storage media may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0100] The processor can call the information and application program stored in the storage medium through the transmission system to execute the following steps: Step 101, obtaining a query sentence given by a user and document information of the satellite data document, wherein the query sentence includes: a plurality of terms and the frequency of occurrence of the terms in the query sentence, and the document information includes: the length of the satellite data document and the average length of the satellite data document;

[0101] Step 102, setting a retrieval relevance evaluation model, and calculating a relevance score for evaluating the query sentence given by the user and the satellite data document according to the query sentence and the document information;

[0102] Specifically, the retrieval relevance evaluation model includes:

[0103] ,

[0104] in, To evaluate the query sentence given by the user and satellite data files The correlation score between For query sentence The Terms The inverse document frequency of For query sentence The term, For query sentence The Terms In the query sentence The frequency in is the first adjustment factor for correlation, is the second adjustment factor for correlation, Satellite data files Length, Satellite data files The average length of For the relevant A third adjustment factor, For query sentence and satellite data files The spatial similarity between For query sentence and satellite data files The time similarity between them.

[0105] Specifically, query sentence and satellite data files The spatial similarity between include:

[0106] ,

[0107] in, is the first adjustment factor of spatial similarity, Satellite data files No. The spatial feature vectors, is the transpose of the matrix, is the covariance matrix, is the second adjustment factor of spatial similarity, For time.

[0108] Specifically, query sentence and satellite data files The time similarity between include:

[0109] ,

[0110] in, is the first adjustment factor of temporal similarity, For query sentence timestamp, Satellite data files The timestamp of the spatial feature vector, is the second adjustment factor of time similarity.

[0111] Specifically, all adjustment factors are fitted by gradient descent method.

[0112] Step 103, setting a relevance threshold, if the relevance score is greater than or equal to the relevance threshold, displaying the satellite data document corresponding to the highest relevance score to the user, otherwise prompting that the query sentence has been retrieved.

[0113] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0114] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0115] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0116] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0117] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0118] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only storage medium (ROM, Read-Only Memory), random access storage medium (RAM, RandomAccess Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0119] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. A method for rapid retrieval of large-scale intelligence data based on a large model, wherein the intelligence data is a satellite data file, characterized in that: include: Acquire a query sentence given by a user and document information of the satellite data document, wherein the query sentence includes: a plurality of terms and the frequency of occurrence of the terms in the query sentence, and the document information includes: the length of the satellite data document and the average length of the satellite data document; Setting a retrieval relevance evaluation model, and calculating a relevance score for evaluating the query sentence given by the user and the satellite data document according to the query sentence and the document information; Setting a relevance threshold, if the relevance score is greater than or equal to the relevance threshold, displaying the satellite data document corresponding to the highest relevance score to the user, otherwise prompting that the query sentence is retrieved; The retrieval relevance evaluation model includes: ， in, To evaluate the query sentence given by the user and satellite data files The correlation score between For query sentence The Terms The inverse document frequency of For query sentence The term, For query sentence The Terms In the query sentence The frequency in is the first adjustment factor for correlation, is the second adjustment factor for correlation, Satellite data files Length, Satellite data files The average length of For the relevant A third adjustment factor, For query sentence and satellite data files The spatial similarity between For query sentence and satellite data files The temporal similarity between Query Sentence and satellite data files The spatial similarity between include: ， in, is the first adjustment factor of spatial similarity, Satellite data files No. The spatial feature vectors, is the transpose of the matrix, is the covariance matrix, is the second adjustment factor of spatial similarity, For time; Query Sentence and satellite data files The time similarity between include: ， in, is the first adjustment factor of temporal similarity, For query sentence timestamp, Satellite data files The timestamp of the spatial feature vector, is the second adjustment factor of time similarity.

2. A method for rapid retrieval of large-scale intelligence data based on a large model as claimed in claim 1, characterized in that: All adjustment factors are fitted by gradient descent method.

3. A fast retrieval system for large-scale intelligence data based on a large model, wherein the intelligence data is a satellite data file, characterized in that: include: An information acquisition module is used to acquire a query sentence given by a user and document information of the satellite data document, wherein the query sentence includes: a plurality of terms and the frequency of occurrence of the terms in the query sentence, and the document information includes: the length of the satellite data document and the average length of the satellite data document; Setting a model module, used to set a retrieval relevance evaluation model, and calculating a relevance score for evaluating the query sentence given by the user and the satellite data document according to the query sentence and the document information; A retrieval module, used for setting a relevance threshold, and if the relevance score is greater than or equal to the relevance threshold, displaying the satellite data document corresponding to the highest relevance score to the user, otherwise prompting that the query sentence is retrieved; The retrieval relevance evaluation model includes: ， in, To evaluate the query sentence given by the user and satellite data files The correlation score between For query sentence The Terms The inverse document frequency of For query sentence The term, For query sentence The Terms In the query sentence The frequency in is the first adjustment factor for correlation, is the second adjustment factor for correlation, Satellite data files Length, Satellite data files The average length of For the relevant A third adjustment factor, For query sentence and satellite data files The spatial similarity between For query sentence and satellite data files The temporal similarity between Query Sentence and satellite data files The spatial similarity between include: ， in, is the first adjustment factor of spatial similarity, Satellite data files No. The spatial feature vectors, is the transpose of the matrix, is the covariance matrix, is the second adjustment factor of spatial similarity, For time; Query Sentence and satellite data files The time similarity between include: ， in, is the first adjustment factor of temporal similarity, For query sentence timestamp, Satellite data files The timestamp of the spatial feature vector, is the second adjustment factor of time similarity.

4. A rapid retrieval system for large-scale intelligence data based on a large model as claimed in claim 3, characterized in that: All adjustment factors are fitted by gradient descent method.

Images