Information processing method, device, electronic device and storage medium

Abstract

The present disclosure provides an information processing method, apparatus, electronic device, and storage medium, relating to the fields of artificial intelligence technology, specifically document processing and smart office technology. A specific implementation scheme comprises: obtaining target information, the target information comprising at least a portion of the content of a long document, or input information associated with the long document; generating a first candidate graph for the long document using a large model based on the target information; obtaining a second candidate graph from a graph database based on the target information; associating the first and second candidate graphs corresponding to the same document content to obtain a group of associated candidate graphs; and generating a target graph for the same document content based on the group of associated candidate graphs.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to the field of document processing and smart office technology, and in particular to an information processing method, device, electronic device and storage medium. Background Art

[0002] When long, general documents lack relevant charts and graphs, a common approach is to manually draw appropriate tables and graphs, embedding them in appropriate locations according to the text's outline. This entire process requires repeated revisions and re-expression to ultimately complete the document. This extensive manual intervention makes the entire process difficult to automate, resulting in low efficiency. Furthermore, the information retrieved to construct the charts and graphs may not be comprehensive. Summary of the Invention

[0003] The present disclosure provides an information processing method, apparatus, electronic device, and storage medium.

[0004] According to one aspect of the present disclosure, an information processing method is provided, comprising: obtaining target information, the target information including at least part of the content of the long document, or input information associated with the long document; generating a first candidate graph for the long document based on the target information using a large model; obtaining a second candidate graph from a graph database based on the target information; associating the first candidate graph and the second candidate graph corresponding to the same document content to obtain an associated candidate graph group, and generating a target graph for the same document content based on the associated candidate graph group.

[0005] According to another aspect of the present disclosure, an information processing device is provided, including: a first acquisition module for acquiring target information, wherein the target information includes at least part of the content of the long document, or is input information associated with the long document; a first generation module for generating a first candidate chart of the long document according to the target information through a large model; a second acquisition module for acquiring a second candidate chart from a chart database according to the target information; and a second generation module for associating the first candidate chart and the second candidate chart corresponding to the same document content to obtain an associated candidate chart group, and generating a target chart of the same document content based on the associated candidate chart group.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the information processing method described in the above-mentioned embodiment.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, on which a computer program / instruction is stored. The computer instructions are used to enable the computer to execute the information processing method described in the embodiment of the above aspect.

[0008] According to another aspect of the present disclosure, a computer program product is provided, including a computer program / instruction, which implements the information processing method described in the embodiment of the first aspect when executed by a processor.

[0009] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0011] Figure 1 A flowchart of an information processing method provided by an embodiment of the present disclosure;

[0012] Figure 2 A flowchart of another information processing method provided by an embodiment of the present disclosure;

[0013] Figure 3 A flowchart of another information processing method provided by an embodiment of the present disclosure;

[0014] Figure 4 A flowchart of another information processing method provided by an embodiment of the present disclosure;

[0015] Figure 5 A schematic diagram of a process for generating a target chart according to an embodiment of the present disclosure;

[0016] Figure 6 A schematic diagram of the structure of an information processing device provided in an embodiment of the present disclosure;

[0017] Figure 7 A block diagram of an electronic device for implementing the information processing method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0019] The information processing method, apparatus, and electronic device according to the embodiments of the present disclosure are described below with reference to the accompanying drawings.

[0020] Artificial Intelligence (AI) is the study of how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). This discipline encompasses both hardware and software technologies. AI hardware technologies generally include computer vision, speech recognition, natural language processing, as well as deep learning / learning, big data processing, and knowledge graphs.

[0021] Figure 1 A flowchart of an information processing method provided in an embodiment of the present disclosure.

[0022] like Figure 1 As shown, the information processing method may include:

[0023] S101 : Acquire target information, where the target information includes at least a portion of the content in the long document, or is input information associated with the long document.

[0024] It should be noted that the execution entity of the information processing method in the embodiments of the present disclosure may be a hardware device with data processing capabilities and / or the necessary software to drive the operation of the hardware device. Optionally, the execution entity may include a server, a user terminal, and other intelligent devices. Optionally, the user terminal includes but is not limited to a mobile phone, a computer, an intelligent voice interaction device, etc. Optionally, the server includes but is not limited to a network server, an application server, a server of a distributed system, or a server integrated with a blockchain, etc. This is not specifically limited in the embodiments of the present disclosure.

[0025] In some implementations, a long document can be obtained from a search engine or document database, and the target information can be determined based on the long document. Alternatively, a portion of the content of the long document can be intercepted and used as the target information. For example, the portion of the content for which a chart is to be generated can be used as the target information.

[0026] In some implementations, a user may also determine input information based on a long document and use the input information as target information. In other words, the input information refers to information related to the long document, but not necessarily directly contained within the document. For example, the subject information of the long document may be used as input information associated with the long document.

[0027] S102: Generate a first candidate graph of the long document according to the target information using the large model.

[0028] In some implementations, key search terms for the target information can be determined, and the large model can generate a chart for the long document based on the key search terms as a first candidate chart. Alternatively, a search can be performed based on the key search terms to obtain reference information useful for generating the chart, and the large model can fuse the reference information to obtain the first candidate chart.

[0029] Optionally, keyword recognition can be performed on the target information, and the recognized keywords can be used as key search terms for the target information. For example, key search terms can be determined based on information such as the type and subject of the chart. If a bar chart appears, the bar chart can be used as the key search term.

[0030] In some implementations, key search terms can be used to search an external search engine to identify reference information relevant to chart generation. Reference information can include numerical data, text descriptions, images, and other information. Furthermore, the reference information is integrated using a large model. By processing and analyzing the reference information, the large model can determine relationships and trends among the reference information and, based on these relationships and trends, generate a first candidate chart.

[0031] S103 : Acquire a second candidate graph from the graph database according to the target information.

[0032] In some implementations, key search terms of target information are determined and vectorized to obtain vector representations corresponding to the key search terms. Similarity matching is performed in a graph database based on the vector representations, and a second candidate graph is determined based on the similarity.

[0033] Alternatively, multiple charts with a threshold similarity score to the vector representation may be obtained, the multiple charts may be sorted based on the similarity scores, and the sorted charts may be used as the second candidate charts. Alternatively, a predetermined number of charts may be provided, and based on the similarity scores, N charts with the highest similarity scores to the vector representation may be identified from a chart database, and the N charts may be sorted to obtain the second candidate charts. N is a natural number greater than 1.

[0034] S104 , associating the first candidate graph and the second candidate graph corresponding to the same document content to obtain an associated candidate graph group, and generating a target graph for the same document content based on the associated candidate graph group.

[0035] In some implementations, the associated candidate chart group may be obtained by determining the document content corresponding to each of the first candidate chart and the second candidate chart, and associating the first candidate chart and the second candidate chart with the same document content.

[0036] Furthermore, a target chart for the same document content can be determined based on the first and second candidate charts in the associated candidate chart group. Optionally, a weighted fusion of the first and second candidate charts can be performed to obtain the target chart. Optionally, the confidence levels of the first and second candidate charts can be determined, and the candidate chart with the higher confidence level can be selected as the target chart.

[0037] According to the information processing method provided by the embodiments of the present disclosure, target information for a long document is determined. Based on this target information, a large model determines a first candidate chart for the long document and, based on this target information, a second candidate chart is determined from a chart database. Furthermore, based on the first and second candidate charts, a target chart corresponding to the long document can be determined. The solution provided by the present disclosure can quickly generate accurate, professional charts that are tailored to the current document content. Furthermore, during the document chart generation process, human intervention is significantly reduced, thereby improving the professionalism of document generation and shortening the time required for chart generation.

[0038] Figure 2 A flowchart of an information processing method provided in an embodiment of the present disclosure.

[0039] like Figure 2 As shown, the information processing method may include:

[0040] S201 : Acquire target information, where the target information includes at least a portion of the content in the long document, or is input information associated with the long document.

[0041] The relevant contents of step S201 can be found in the above embodiment and will not be repeated here.

[0042] S202: Determine key search terms according to target information, and obtain reference information for graph generation based on the key search terms.

[0043] In some implementations, the document content for which a chart needs to be generated can be determined from the target information, and keyword recognition can be performed on the document content to determine key search terms, thereby improving information retrieval efficiency and ensuring the quality of retrieved information.

[0044] Optionally, by performing content recognition on the target information, the document content for which the chart is to be generated is obtained, and key search terms are determined based on the document content for generating the chart. The key search terms can be determined by identifying keywords related to the chart in the document content.

[0045] Furthermore, key search terms can be used to search for diagram generation information in an external search engine to determine reference information for diagram generation. Using key search terms can quickly find reference information related to diagram generation in the search engine, improving search efficiency and accuracy.

[0046] Alternatively, an external search engine may be used to search for the key search terms. A search request including the key search terms is sent to the external search engine via the target interface. Upon receiving the search request, the external search engine uses the key search terms to perform a search and obtain initial search information.

[0047] Furthermore, by receiving initial search information fed back by the search engine, the initial search information is retrieved by the search engine based on the key search terms, and then valid information is extracted from the initial search information to obtain reference information. Optionally, information related to the chart can be used as valid information, and valid information can be extracted to obtain reference information.

[0048] S203 , performing information fusion on the reference information through the large model to obtain fused information, and generating a first candidate graph based on the fused information.

[0049] Optionally, fusion can be performed based on the features of the reference information to obtain fused information. Feature extraction is performed on the reference information to obtain a feature vector with semantic information, and the feature vector machine is fused using a large model to obtain fused information.

[0050] Furthermore, a chart type may be determined based on the fusion information, and the fusion information may be visualized in the form of a chart to obtain a first candidate chart. For example, the chart type may be determined to be a line chart, and the fusion information may be visualized in the form of a line chart to obtain a first candidate chart.

[0051] S204 : Acquire a second candidate graph from the graph database according to the target information.

[0052] S205 , associating the first candidate graph and the second candidate graph corresponding to the same document content to obtain an associated candidate graph group, and generating a target graph for the same document content based on the associated candidate graph group.

[0053] The relevant contents of steps S204-S205 can be found in the above embodiment and will not be repeated here.

[0054] According to the information processing method provided by the embodiment of the present disclosure, the target information of the long document is determined, and the key search terms are determined based on the target information. Then, the reference information for chart generation is determined based on the key search terms, and the first candidate chart for the long document is generated by the large model based on the reference information. Furthermore, based on the target information, the second candidate chart is determined from the chart database. Then, based on the first candidate chart and the second candidate chart, the target chart corresponding to the long document can be determined. The solution provided by the present disclosure can quickly generate accurate, professional charts that fit the current document content, and in the process of generating document charts, it can greatly avoid human intervention, so as to improve the professionalism of document generation and shorten the time spent on chart generation.

[0055] Figure 3 A flowchart of an information processing method provided in an embodiment of the present disclosure.

[0056] like Figure 3 As shown, the information processing method may include:

[0057] S301 : Acquire target information, where the target information includes at least a portion of the content in the long document, or is input information associated with the long document.

[0058] S302: Generate a first candidate graph of the long document according to the target information using the large model.

[0059] The relevant contents of steps S301-S302 can be found in the above embodiment and will not be repeated here.

[0060] S303: Determine a key search term according to the target information, and obtain a first vector representation of the key search term.

[0061] In some implementations, the document content for which a chart needs to be generated can be determined from the target information, and keyword recognition can be performed on the document content to determine key search terms, thereby improving information retrieval efficiency and ensuring the quality of retrieved information.

[0062] Optionally, by performing content recognition on the target information, the document content for which the chart is to be generated is obtained, and key search terms are determined based on the document content for generating the chart. The key search terms can be determined by identifying keywords related to the chart in the document content.

[0063] Furthermore, by vectorizing the key search terms, a first vector representation of the key search terms can be obtained.

[0064] S304 : Retrieve a second candidate graph from the graph database according to the first vector representation of the key search term.

[0065] In some implementations, similarity calculation can be performed based on vector representation to obtain candidate graphs in the graph database that match the key search terms as second candidate graphs. Using the vector similarity calculation method, the candidate graph that best matches the key search terms can be quickly found, thereby improving the flexibility and speed of retrieval.

[0066] Optionally, by obtaining a second vector representation of the candidate graph in the graph database, the first vector representation and the second vector representation can be matched, and at least one candidate graph matching the key search term can be obtained from the graph database based on the matching result. Further, the candidate graphs matching the key search term are sorted to obtain a second candidate graph.

[0067] Optionally, by calculating the similarity between the first vector representation and the second vector, the top N candidate graphs with the highest similarity scores are selected as candidate graphs matching the key search term, and the candidate graphs are then sorted according to the similarity scores, and the sorted candidate graphs are selected as second candidate graphs, where N is a natural number greater than 1.

[0068] S305 , associating the first candidate graph and the second candidate graph corresponding to the same document content to obtain an associated candidate graph group, and generating a target graph for the same document content based on the associated candidate graph group.

[0069] The relevant contents of associating the candidate graphs in step S305 can be found in the above embodiment and will not be described again here.

[0070] In some implementations, by determining the first and second candidate charts in the associated candidate chart group and determining the target chart based on the confidence levels of the candidate charts, it is possible to more accurately determine whether a chart matches the content of a long document, thereby improving the accuracy of chart generation. Specifically, by obtaining the confidence levels of the first and second candidate charts, the candidate chart with the higher confidence level is selected as the target chart.

[0071] In some implementations, the candidate charts can be weightedly fused based on the confidence levels of the first candidate chart and the second candidate chart to obtain a target chart. Through weighted fusion, the information of the first candidate chart and the second candidate chart can be comprehensively considered, thereby improving the accuracy and reliability of the target chart.

[0072] Optionally, the confidence scores of the first candidate graph and the second candidate graph are obtained, and fusion weights of the first candidate graph and the second candidate graph are determined based on the confidence scores. Furthermore, the first candidate graph and the second candidate graph are fused based on the fusion weights to obtain a target graph.

[0073] According to the information processing method provided by the embodiments of the present disclosure, the target information of a long document is determined, and a large model determines a first candidate chart for the long document based on the target information. Furthermore, a key search term is determined based on the target information, and a second candidate chart is determined from a chart database based on the key search term. Furthermore, the target chart corresponding to the long document can be determined based on the confidence level of the first and second candidate charts. The solution provided by the present disclosure can quickly generate accurate, professional charts that match the current document content. Furthermore, during the process of generating document charts, human intervention is greatly reduced, thereby improving the professionalism of document generation and shortening the time required for chart generation.

[0074] Figure 4 A flowchart of an information processing method provided in an embodiment of the present disclosure.

[0075] like Figure 4 As shown, the information processing method may include:

[0076] S401 : Acquire target information, where the target information includes at least a portion of the content in the long document, or is input information associated with the long document.

[0077] S402: Generate a first candidate graph of the long document according to the target information using the large model.

[0078] S403: Obtain a second candidate graph from the graph database according to the target information.

[0079] S404 , associating the first candidate graph and the second candidate graph corresponding to the same document content to obtain an associated candidate graph group, and generating a target graph for the same document content based on the associated candidate graph group.

[0080] The relevant contents of steps S401-S404 can be found in the above embodiment and will not be repeated here.

[0081] S405 , determining an insertion position of a target chart in the long document, and inserting the target chart at the insertion position.

[0082] In some implementations, after generating a target chart corresponding to a long document, the target chart can be inserted at the insertion position in the long document by determining the insertion position, thereby obtaining complete, effective, and highly professional long document content.

[0083] In some implementations, the position of the key search term associated with the target graph can be determined and used as the insertion position of the target graph in the long document, which can ensure that the narrative logic of the document is more coherent and improve the readability and comprehension of the long document.

[0084] Alternatively, a second candidate chart corresponding to the target chart can be obtained, and the key search term associated with the target chart can be determined based on the second candidate chart. Alternatively, the first vector representation that matches the second vector representation of the second candidate chart can be obtained, and the key search term associated with the target chart can be determined based on the matched first vector representation. In other words, the key search term used when determining the second candidate chart can be used as the key search term associated with the target chart, thereby enhancing the relevance between the icon and the document, thereby improving the quality of the document.

[0085] Furthermore, the target chart can be inserted into the long document based on the key search terms associated with the target chart. Alternatively, the long document can be searched based on the key search terms to determine the position of the key search terms in the long document, and the position can be used as the insertion position of the target chart in the long document.

[0086] According to the information processing method provided by the embodiment of the present disclosure, the target information of the long document is determined, and the large model determines the first candidate chart of the long document based on the target information, and determines the second candidate chart from the chart database based on the target information. Then, the target chart corresponding to the long document can be determined based on the first candidate chart and the second candidate chart. Furthermore, the generated target chart can be inserted into the long document to obtain complete, effective, and highly professional long document content. The solution provided by the present disclosure can quickly generate accurate, professional, and consistent charts for the current document content, and in the process of generating document charts, it greatly avoids human intervention, so as to improve the professionalism of document generation and shorten the time spent on chart generation.

[0087] like Figure 5 The following is a flow chart illustrating the process of generating a target graph. By obtaining key search terms from the target information and using them to search an external search engine, initial search information related to graph generation can be obtained. Reference information can then be extracted from this initial search information. Furthermore, the large model fuses this reference information to obtain the first candidate graph for the long document.

[0088] By vectorizing the key search terms, a first vector representation corresponding to the key search terms can be obtained, and a second vector representation of the candidate graph in the graph database can be obtained. By matching the first vector representation and the second vector representation, a candidate graph matching the key search terms can be obtained, and the candidate graphs can be sorted to obtain a second candidate graph.

[0089] Furthermore, confidence levels of the first candidate graph and the second candidate graph are determined, so as to generate a target graph based on the confidence levels and the first candidate graph and the second candidate graph.

[0090] Corresponding to the information processing methods provided in the above-mentioned embodiments, an embodiment of the present disclosure also provides an information processing device. Since the information processing device provided in the embodiment of the present disclosure corresponds to the information processing methods provided in the above-mentioned embodiments, the implementation methods of the above-mentioned information processing methods are also applicable to the information processing device provided in the embodiment of the present disclosure and will not be described in detail in the following embodiments.

[0091] Figure 6 A schematic diagram of the structure of an information processing device provided in an embodiment of the present disclosure.

[0092] like Figure 6 As shown, the information processing device 600 of the embodiment of the present disclosure includes a first acquisition module 601 , a first generation module 602 , a second acquisition module 603 and a second generation module 604 .

[0093] A first acquisition module 601 is configured to acquire target information, where the target information includes at least a portion of the content of the long document, or is input information associated with the long document;

[0094] A first generating module 602 is configured to generate a first candidate graph for the long document according to the target information using a large model;

[0095] A second acquisition module 603 is configured to acquire a second candidate chart from a chart database according to the target information;

[0096] The second generating module 604 is configured to associate the first candidate graph and the second candidate graph corresponding to the same document content to obtain an associated candidate graph group, and generate a target graph for the same document content based on the associated candidate graph group.

[0097] In one embodiment of the present disclosure, the first generation module 602 is further used to: determine key search terms according to the target information, and obtain reference information for chart generation based on the key search terms; fuse the reference information through the large model to obtain fused information, and generate the first candidate chart based on the fused information.

[0098] In one embodiment of the present disclosure, the first generation module 602 is further used to: send a search request to an external search engine through a target interface, wherein the search request includes the key search term; receive initial search information fed back by the search engine, wherein the initial search information is obtained by the search engine performing information retrieval based on the key search term; and extract effective information from the initial search information to obtain the reference information.

[0099] In one embodiment of the present disclosure, the second acquisition module 603 is further configured to: determine a key search term based on the target information, and obtain a first vector representation of the key search term; and retrieve the second candidate graph from the graph database based on the first vector representation of the key search term.

[0100] In one embodiment of the present disclosure, the second acquisition module 603 is further used to: obtain a second vector representation of the candidate graph in the graph database; match the first vector representation and the second vector representation, and obtain at least one candidate graph matching the key search term from the graph database based on the matching result; and sort the candidate graphs matching the key search term to obtain the second candidate graph.

[0101] In one embodiment of the present disclosure, the first generating module 602 is further configured to: perform content recognition on the target information to obtain document content for which a chart needs to be generated; and determine the key search term based on the document content for which a chart needs to be generated.

[0102] In one embodiment of the present disclosure, the second generating module 604 is further configured to obtain the confidence scores of the first candidate chart and the second candidate chart, and select the candidate chart with the higher confidence score as the target chart.

[0103] In one embodiment of the present disclosure, the second generation module 604 is further configured to: obtain the confidence scores of the first candidate chart and the second candidate chart; determine the fusion weights of the first candidate chart and the second candidate chart based on the confidence scores of the first candidate chart and the second candidate chart; and fuse the first candidate chart and the second candidate chart based on the fusion weights to obtain the target chart.

[0104] In one embodiment of the present disclosure, the second generating module 604 is further configured to determine an insertion position of the target chart in the long document, and insert the target chart at the insertion position.

[0105] In one embodiment of the present disclosure, the second generation module 604 is further used to: obtain a second candidate chart corresponding to the target chart; determine the key search terms associated with the target chart based on the second candidate chart; and determine the insertion position of the target chart in the long document based on the key search terms associated with the target chart.

[0106] In one embodiment of the present disclosure, the second generating module 604 is further configured to obtain a first vector representation matched by the second vector representation of the second candidate graph, and determine a key search term associated with the target graph according to the matched first vector representation.

[0107] According to the information processing device provided by the embodiments of the present disclosure, by determining the target information of a long document, a large model determines a first candidate chart for the long document based on the target information, and also determines a second candidate chart from a chart database based on the target information. Furthermore, the target chart corresponding to the long document can be determined based on the first and second candidate charts. The solution provided by the present disclosure can quickly generate accurate, professional charts that match the current document content. In the process of generating document charts, human intervention is greatly reduced, thereby improving the professionalism of document generation and shortening the time required for chart generation.

[0108] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0109] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0110] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0111] like Figure 7 As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to computer programs / instructions stored in a read-only memory (ROM) 702 or computer programs / instructions loaded from a storage unit 706 into a random access memory (RAM) 703. Various programs and data required for the operation of the device 700 can also be stored in the RAM 703. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0112] Various components in device 700 are connected to I / O interface 705, including: input unit 706, such as a keyboard, mouse, etc.; output unit 707, such as various types of displays, speakers, etc.; storage unit 708, such as a magnetic disk, optical disk, etc.; and communication unit 709, such as a network card, modem, wireless communication transceiver, etc. Communication unit 709 allows device 700 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0113] The computing unit 701 can be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as information processing methods. For example, in some embodiments, the information processing method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as a storage unit 706. In some embodiments, part or all of the computer program / instructions can be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program / instructions are loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the information processing method described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the information processing method by any other appropriate means (e.g., by means of firmware).

[0114] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs / instructions that are executable and / or interpreted on a programmable system comprising at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0115] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0116] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0117] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0118] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0119] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. The client-server relationship arises through computer programs / instructions running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0120] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0121] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. An information processing method, wherein: The method comprises: Acquiring target information, where the target information includes at least a portion of content in a long document, or is input information associated with the long document; generating a first candidate graph for the long document according to the target information using a large model; acquiring a second candidate chart from a chart database according to the target information; Associating a first candidate graph and a second candidate graph corresponding to the same document content to obtain an associated candidate graph group, and generating a target graph for the same document content based on the associated candidate graph group; The step of generating the target graph of the same document content according to the associated candidate graph group includes: Obtaining confidence scores of the first candidate graph and the second candidate graph; determining, according to the confidence scores of the first candidate graph and the second candidate graph, respective fusion weights of the first candidate graph and the second candidate graph; The first candidate graph and the second candidate graph are fused according to the fusion weight to obtain the target graph.

2. The method according to claim 1, wherein Generating a first candidate graph for the long document according to the target information using the large model includes: Determining key search terms according to the target information, and acquiring reference information for generating a chart based on the key search terms; The reference information is fused using the large model to obtain fused information, and the first candidate graph is generated based on the fused information.

3. The method according to claim 2, wherein: The step of obtaining reference information for generating a chart based on the key search term includes: Sending a search request to an external search engine via a target interface, wherein the search request includes the key search term; receiving initial search information fed back by the search engine, wherein the initial search information is obtained by the search engine through information retrieval based on the key search term; Effective information is extracted from the initial search information to obtain the reference information.

4. The method according to claim 1, wherein The step of obtaining a second candidate chart from a chart database according to the target information includes: Determining a key search term based on the target information, and obtaining a first vector representation of the key search term; The second candidate graph is retrieved from the graph database according to the first vector representation of the key search term.

5. The method according to claim 4, wherein The retrieving the second candidate graph from the graph database according to the first vector representation of the key search term includes: obtaining a second vector representation of the candidate graph in the graph database; matching the first vector representation and the second vector representation, and obtaining at least one candidate graph matching the key search term from the graph database according to the matching result; The candidate graphs matching the key search term are sorted to obtain the second candidate graph.

6. The method according to claim 2 or 4, wherein: Determining a key search term based on the target information includes: Performing content recognition on the target information to obtain the document content for which a chart needs to be generated; The key search term is determined according to the document content of the generated chart.

7. The method according to any one of claims 1 to 4, wherein The step of generating the target graph for the same document content according to the associated candidate graph group further includes: The confidence levels of the first candidate graph and the second candidate graph are obtained, and the candidate graph with the higher confidence level is selected as the target graph.

8. The method according to any one of claims 1 to 4, wherein After generating the target graph of the same document content according to the associated candidate graph group, the method further includes: An insertion position of the target chart in the long document is determined, and the target chart is inserted at the insertion position.

9. The method according to claim 8, wherein Determining the insertion position of the target chart in the long document includes: Obtaining a second candidate chart corresponding to the target chart; determining a key search term associated with the target graph based on the second candidate graph; An insertion position of the target graph in the long document is determined according to a key search term associated with the target graph.

10. The method according to claim 8, wherein The step of determining a key search term associated with the target graph based on the second candidate graph includes: The first vector representation matched by the second vector representation of the second candidate graph is obtained, and a key search term associated with the target graph is determined according to the matched first vector representation.

11. An information processing device, wherein: The device comprises: A first acquisition module is configured to acquire target information, wherein the target information includes at least a portion of the content of the long document, or is input information associated with the long document; A first generating module, configured to generate a first candidate graph for the long document according to the target information using a large model; a second acquisition module, configured to acquire a second candidate chart from a chart database according to the target information; a second generating module configured to associate a first candidate graph and a second candidate graph corresponding to the same document content to obtain an associated candidate graph group, and generate a target graph for the same document content based on the associated candidate graph group; The second generation module is also used to: Obtaining confidence scores of the first candidate graph and the second candidate graph; determining, according to the confidence scores of the first candidate graph and the second candidate graph, respective fusion weights of the first candidate graph and the second candidate graph; The first candidate graph and the second candidate graph are fused according to the fusion weight to obtain the target graph.

12. The device according to claim 11, wherein The first generating module is further configured to: Determining key search terms according to the target information, and acquiring reference information for generating a chart based on the key search terms; The reference information is fused using the large model to obtain fused information, and the first candidate graph is generated based on the fused information.

13. The device according to claim 12, wherein The first generating module is further configured to: Sending a search request to an external search engine via a target interface, wherein the search request includes the key search term; receiving initial search information fed back by the search engine, wherein the initial search information is obtained by the search engine through information retrieval based on the key search term; Effective information is extracted from the initial search information to obtain the reference information.

14. The device according to claim 11, wherein The second acquisition module is further configured to: Determining a key search term based on the target information, and obtaining a first vector representation of the key search term; The second candidate graph is retrieved from the graph database according to the first vector representation of the key search term.

15. The device according to claim 14, wherein The second acquisition module is further configured to: obtaining a second vector representation of the candidate graph in the graph database; matching the first vector representation and the second vector representation, and obtaining at least one candidate graph matching the key search term from the graph database according to the matching result; The candidate graphs matching the key search term are sorted to obtain the second candidate graph.

16. The device according to claim 12 or 14, wherein The first generating module is further configured to: Performing content recognition on the target information to obtain the document content for which a chart needs to be generated; The key search term is determined according to the document content of the generated chart.

17. The device according to any one of claims 11 to 14, wherein: The second generating module is further configured to: The confidence levels of the first candidate graph and the second candidate graph are obtained, and the candidate graph with the higher confidence level is selected as the target graph.

18. The device according to any one of claims 11 to 14, wherein: The second generating module is further configured to: An insertion position of the target chart in the long document is determined, and the target chart is inserted at the insertion position.

19. The device according to claim 18, wherein The second generating module is further configured to: Obtaining a second candidate chart corresponding to the target chart; determining a key search term associated with the target graph based on the second candidate graph; An insertion position of the target graph in the long document is determined according to a key search term associated with the target graph.

20. The apparatus according to claim 18, wherein The second generating module is further configured to: The first vector representation matched by the second vector representation of the second candidate graph is obtained, and a key search term associated with the target graph is determined according to the matched first vector representation.

21. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-10.

23. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images