Investment transaction monitoring method and device based on investment research report

Abstract

The present invention provides an investment transaction monitoring method and device based on investment research reports, which relates to the field of artificial intelligence technology. The method includes: by obtaining investment research report data, extracting N key data from the investment research report data based on preset key event factors; inputting the N key data into a preset recurrent neural network model to obtain the state value corresponding to each key data; inputting M key data whose state values are specific values into a preset recurrent neural network model to obtain the predicted state value corresponding to each key data; determining a classification data indicator based on a first number of specific values in the predicted state values and a second number of specific values in the state values; determining a monitoring threshold based on the classification data indicator, and monitoring newly added investment transactions according to the monitoring threshold. The present invention can greatly reduce manpower and time costs and improve the investment research efficiency of bank wealth management.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and device for monitoring investment transactions based on investment research reports. Background Art

[0002] Currently, investment research reports in the banking asset management sector are primarily managed through manual upload, maintenance, and archiving. This involves downloading reports from external networks, manually uploading them to the bank's asset management system, and manually archiving and maintaining them. Finally, reviewing the reports provides an important reference for investment transactions.

[0003] With the increasing number of external investment research reports, manual maintenance can no longer meet business needs and consumes enormous manpower and time. Furthermore, manually reviewing investment research reports to select appropriate investment portfolio strategies is necessary. However, due to the wide variety and complexity of investment products, this can easily lead to certain forecasting errors when selecting investment portfolio strategies, increasing investment transaction risks. Summary of the Invention

[0004] To address the problems in the prior art, the present invention provides a method and device for monitoring investment transactions based on investment research reports, which specifically include the following technical solutions:

[0005] In a first aspect, the present invention provides an investment transaction monitoring method based on an investment research report, comprising:

[0006] Obtain investment research report data, and extract N key data from the investment research report data based on preset key event factors;

[0007] Inputting N key data into a preset recurrent neural network model to obtain a state value corresponding to each key data; inputting M key data whose state values are specific values into a preset recurrent neural network model to obtain a predicted state value corresponding to each key data;

[0008] determining a classification data indicator based on a first number of specific values in the predicted state values and a second number of specific values in the state values;

[0009] Determining a monitoring threshold based on the classification data indicator, and monitoring new investment transactions according to the monitoring threshold;

[0010] Wherein, N and M are positive integers greater than 1, and N is greater than M.

[0011] Furthermore, after obtaining the investment research report data, the following is also included:

[0012] If it is determined that the investment research report data is unstructured data, the unstructured investment research report data is converted into semi-structured investment research report data.

[0013] The determining of the classification data indicator based on the first number of specific values in the predicted state value and the second number of specific values in the state value includes:

[0014] Four arithmetic operations are performed according to the first quantity and the second quantity, and results of the four arithmetic operations are determined as classification data indicators.

[0015] The step of determining a monitoring threshold based on the classification data indicator includes:

[0016] According to the difference threshold corresponding to the classification data indicator, the monitoring threshold is obtained by calculation based on the classification data indicator and the difference threshold.

[0017] The step of monitoring the newly added investment transactions according to the monitoring threshold includes:

[0018] Determine the classification data indicator corresponding to the newly added investment transaction. If the classification data indicator corresponding to the newly added investment transaction is not within the monitoring threshold range, perform early warning processing on the newly added investment transaction.

[0019] In a second aspect, the present invention provides an investment transaction monitoring device based on an investment research report, comprising:

[0020] An extraction module is used to obtain investment research report data and extract N key data from the investment research report data based on preset key event factors;

[0021] A prediction module is used to input N key data into a preset recurrent neural network model to obtain a state value corresponding to each key data; input M key data whose state values are specific values into the preset recurrent neural network model to obtain a predicted state value corresponding to each key data;

[0022] an indicator module for determining a classification data indicator based on a first number of specific values in the predicted state values and a second number of specific values in the state values;

[0023] A monitoring module, configured to determine a monitoring threshold based on the classification data indicator, and monitor new investment transactions according to the monitoring threshold;

[0024] Wherein, N and M are positive integers greater than 1, and N is greater than M.

[0025] Furthermore, it also includes:

[0026] The conversion module is used to convert the unstructured investment research report data into semi-structured investment research report data if it is determined that the investment research report data is unstructured data.

[0027] Wherein, the indicator module includes:

[0028] A calculation unit is used to perform four arithmetic operations according to the first quantity and the second quantity, and determine the results of the four arithmetic operations as a classification data indicator.

[0029] Wherein, the monitoring module includes:

[0030] A calculation unit is used to calculate the monitoring threshold based on the classification data indicator and the difference threshold according to the difference threshold corresponding to the classification data indicator.

[0031] Wherein, the monitoring module includes:

[0032] The early warning unit is used to determine the classification data index corresponding to the newly added investment transaction, and if the classification data index corresponding to the newly added investment transaction is not within the monitoring threshold range, perform early warning processing on the newly added investment transaction.

[0033] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the investment transaction monitoring method based on investment research reports are implemented.

[0034] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the investment transaction monitoring method based on the investment research report.

[0035] As can be seen from the above technical solution, the present invention provides an investment transaction monitoring method and device based on investment research reports. By acquiring investment research report data, N key data are extracted from the investment research report data based on preset key event factors; the N key data are input into a preset recurrent neural network model to obtain the state value corresponding to each key data; M key data with specific state values are input into a preset recurrent neural network model to obtain the predicted state value corresponding to each key data; a classification data indicator is determined based on a first number of specific values in the predicted state values and a second number of specific values in the state values; a monitoring threshold is determined based on the classification data indicator, and new investment transactions are monitored according to the monitoring threshold. This can greatly reduce manpower and time costs and improve the investment research efficiency of bank wealth management. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 Schematic diagram of the first process of the investment transaction monitoring method based on investment research reports in an embodiment of the present invention.

[0038] Figure 2 2 is a schematic diagram of a second flow chart of the investment transaction monitoring method based on investment research reports in an embodiment of the present invention.

[0039] Figure 3 The figure is a flow chart of an investment transaction monitoring method based on investment research reports in a full-process embodiment of the present invention.

[0040] Figure 4 Schematic diagram of the first structure of the investment transaction monitoring device based on the investment research report in an embodiment of the present invention.

[0041] Figure 5 2 is a schematic diagram of the second structure of the investment transaction monitoring device based on the investment research report in an embodiment of the present invention.

[0042] Figure 6 Schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0044] The present invention provides an embodiment of an investment transaction monitoring method based on an investment research report, see Figure 1 The investment transaction monitoring method based on the investment research report specifically includes the following contents:

[0045] S101: Acquire investment research report data, and extract N key data from the investment research report data based on preset key event factors;

[0046] In this step, an automated processing mechanism for external investment research reports is established based on RPA technology, enabling the automatic collection of these reports. The RPA robot periodically pulls the configured automatic recognition rule interface for investment research reports, collects them, and archives them. Using asynchronous queuing technology, the unstructured data in investment research reports is automatically archived into the EAP image.

[0047] It should be noted that RPA, or Robotic Process Automation, can quickly improve business efficiency, automate repetitive work, and connect different business systems with high efficiency and low barriers, allowing industries such as finance, taxation, finance, human resources, information technology, insurance, customer service, operators, and manufacturing to achieve automated and intelligent upgrades in business processes.

[0048] In this embodiment, the key event factors are keywords or key words, and key data are extracted through the ElasticSearch full-text search engine to form a key data set, which further forms an initial data set.

[0049] Elasticsearch is a distributed, highly scalable, and highly real-time search and data analysis engine. It easily enables the search, analysis, and exploration of large amounts of data. Leveraging Elasticsearch's horizontal scalability can make data more valuable in production environments.

[0050] S102: Input N key data into a preset recurrent neural network model to obtain a state value corresponding to each key data; input M key data whose state values are specific values into a preset recurrent neural network model to obtain a predicted state value corresponding to each key data; wherein N and M are positive integers greater than 1, and N is greater than M.

[0051] In this step, unsupervised training is performed in advance based on the training data in the key data set and the recurrent neural network (RNN) machine learning algorithm to obtain a recurrent neural network model.

[0052] In specific implementation, the key data sets are used as input parameters of the recurrent neural network model, and the recurrent neural network model outputs the status values corresponding to each key data, forming the status values of investment research reports of different dimensions.

[0053] Furthermore, according to the classification task, the state value corresponding to each key data output by the ring neural network model is passed to the softmax function for classification.

[0054] S103: Determine a classification data indicator based on a first number of specific values in the predicted state value and a second number of specific values in the state value;

[0055] In this step, four arithmetic operations are performed on the first quantity and the second quantity, and the results of the four arithmetic operations are determined as the classification data indicator. Specifically, the ratio of the first quantity to the second quantity is used as the classification data indicator.

[0056] S104: Determine a monitoring threshold based on the classification data indicator, and monitor new investment transactions according to the monitoring threshold;

[0057] In this step, the difference threshold corresponding to the classification data indicator is first determined. The difference threshold can be set as needed. In this embodiment, the difference threshold is 10%. The monitoring threshold is calculated based on the classification data indicator and the difference threshold. The monitoring threshold is calculated as plus or minus 10% of the value corresponding to the classification data indicator.

[0058] When monitoring new investment transactions according to the monitoring threshold, the classification data indicators corresponding to the new investment transactions are determined. If the classification data indicators corresponding to the new investment transactions are not within the monitoring threshold range, the new investment transactions are warned.

[0059] As can be seen from the above description, the investment transaction monitoring method based on investment research reports provided by the embodiment of the present invention obtains investment research report data, extracts N key data from the investment research report data based on preset key event factors; inputs the N key data into a preset recurrent neural network model to obtain the state value corresponding to each key data; inputs M key data with specific state values into a preset recurrent neural network model to obtain the predicted state value corresponding to each key data; determines a classification data indicator based on a first number of specific values in the predicted state values and a second number of specific values in the state values; determines a monitoring threshold based on the classification data indicator, and monitors newly added investment transactions according to the monitoring threshold. This can greatly reduce manpower and time costs and improve the investment research efficiency of bank wealth management.

[0060] In one embodiment of the present invention, see Figure 2 The investment transaction monitoring method based on the investment research report specifically includes the following contents:

[0061] S105: If it is determined that the investment research report data is unstructured data, the unstructured investment research report data is converted into semi-structured investment research report data.

[0062] In this step, if an automated processing mechanism for external investment research reports is established based on RPA technology, the obtained investment research reports are unstructured data. This unstructured investment research report data needs to be converted into semi-structured investment research report data.

[0063] Specifically, through OCR (optical character recognition) text recognition and chart recognition technology, the investment research report is converted into semi-structured data and archived in the ElasticSearch full-text search engine. Then, the next step of data preprocessing is carried out.

[0064] It should be noted that OCR (optical character recognition) refers to the process of an electronic device (such as a scanner or digital camera) examining characters printed on paper and then translating the shapes into computer text using character recognition methods; that is, the process of scanning text materials and then analyzing and processing the image files to obtain text and layout information.

[0065] From the above technical solution, it can be seen that the automatic collection of external investment research reports and intelligent identification of investment research report texts and charts are achieved through RPA, thereby realizing the automatic collection of external investment research reports.

[0066] To further illustrate this solution, the present invention provides a full-process embodiment of an investment transaction monitoring method based on an investment research report, see Figure 3 The investment transaction monitoring method based on the investment research report specifically includes the following contents:

[0067] S1: Obtain investment research reports:

[0068] The PA robot automatically collects external investment research reports and inputs the original data of the investment research reports into the EAP imaging platform.

[0069] S2: Text Recognition:

[0070] The original data is parsed through OCR text recognition and icon recognition technology to generate semi-structured data.

[0071] S3: Full-text search:

[0072] By matching key event factors, we extract key data sets from the ElasticSearch full-text search engine as machine learning datasets.

[0073] S4: Indicator calculation:

[0074] Key data is trained through the recurrent neural network (RNN) machine learning algorithm, and indicator data parameters are continuously updated.

[0075] S5: Monitoring and early warning:

[0076] Monitor new transactions and indicator data and issue corresponding alerts.

[0077] The embodiment of the present invention provides a specific implementation of an investment transaction monitoring device based on an investment research report that can realize all the contents of the investment transaction monitoring method based on an investment research report, see Figure 4 The investment transaction monitoring device based on the investment research report specifically includes the following contents:

[0078] Extraction module 10, used to obtain investment research report data and extract N key data from the investment research report data based on preset key event factors;

[0079] The prediction module 20 is used to input N key data into a preset recurrent neural network model to obtain a state value corresponding to each key data; input M key data whose state values are specific values into the preset recurrent neural network model to obtain a predicted state value corresponding to each key data;

[0080] an indicator module 30 for determining a classification data indicator based on a first number of specific values in the predicted state values and a second number of specific values in the state values;

[0081] A monitoring module 40, configured to determine a monitoring threshold based on the classification data indicator, and monitor new investment transactions according to the monitoring threshold;

[0082] Wherein, N and M are positive integers greater than 1, and N is greater than M.

[0083] The indicator module 30 includes:

[0084] A calculation unit is used to perform four arithmetic operations according to the first quantity and the second quantity, and determine the results of the four arithmetic operations as a classification data indicator.

[0085] The monitoring module 40 includes:

[0086] A calculation unit is used to calculate the monitoring threshold based on the classification data indicator and the difference threshold according to the difference threshold corresponding to the classification data indicator.

[0087] The monitoring module 40 includes:

[0088] The early warning unit is used to determine the classification data index corresponding to the newly added investment transaction, and if the classification data index corresponding to the newly added investment transaction is not within the monitoring threshold range, perform early warning processing on the newly added investment transaction.

[0089] In one embodiment of the present invention, see Figure 5 The investment transaction monitoring device based on the investment research report specifically includes the following contents:

[0090] The conversion module 50 is configured to convert the unstructured investment research report data into semi-structured investment research report data if it is determined that the investment research report data is unstructured data.

[0091] The embodiment of the investment transaction monitoring device based on investment research reports provided by the present invention can be specifically used to execute the processing flow of the embodiment of the investment transaction monitoring method based on investment research reports in the above embodiment. Its functions will not be repeated here, and reference can be made to the detailed description of the above method embodiment.

[0092] As can be seen from the above description, the investment transaction monitoring device based on investment research reports provided by the embodiment of the present invention obtains investment research report data, extracts N key data from the investment research report data based on preset key event factors; inputs the N key data into a preset recurrent neural network model to obtain the state value corresponding to each key data; inputs M key data with specific state values into a preset recurrent neural network model to obtain the predicted state value corresponding to each key data; determines a classification data indicator based on a first number of specific values in the predicted state values and a second number of specific values in the state values; determines a monitoring threshold based on the classification data indicator, and monitors newly added investment transactions according to the monitoring threshold. This can greatly reduce manpower and time costs and improve the investment research efficiency of bank wealth management.

[0093] The present application provides an embodiment of an electronic device for implementing all or part of the content of the investment transaction monitoring method based on the investment research report. The electronic device specifically includes the following content:

[0094] A processor, a memory, a communications interface, and a bus; wherein the processor, memory, and communications interface communicate with each other via the bus; the communications interface is used to implement information transmission between related devices; the electronic device may be a desktop computer, a tablet computer, a mobile terminal, etc., but this embodiment is not limited thereto. In this embodiment, the electronic device may be implemented with reference to the embodiment for implementing the investment transaction monitoring method based on the investment research report and the embodiment for implementing the investment transaction monitoring device based on the investment research report, the contents of which are incorporated herein and repeated parts are not repeated.

[0095] Figure 6 Schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Figure 6 As shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It is worth noting that the Figure 6is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0096] In one embodiment, the investment transaction monitoring function based on the investment research report can be integrated into the central processing unit 9100. The central processing unit 9100 can be configured to perform the following control:

[0097] Acquire investment research report data, and extract N key data from the investment research report data based on preset key event factors; input the N key data into a preset recurrent neural network model to obtain a state value corresponding to each key data; input M key data whose state values are specific values into a preset recurrent neural network model to obtain a predicted state value corresponding to each key data; determine a classification data indicator based on a first number of specific values in the predicted state values and a second number of specific values in the state values; determine a monitoring threshold based on the classification data indicator, and monitor new investment transactions according to the monitoring threshold.

[0098] As can be seen from the above description, the electronic device provided by the embodiment of the present application obtains investment research report data, extracts N key data from the investment research report data based on preset key event factors; inputs the N key data into a preset recurrent neural network model to obtain a state value corresponding to each key data; inputs M key data whose state values are specific values into a preset recurrent neural network model to obtain a predicted state value corresponding to each key data; determines a classification data indicator based on a first number of specific values in the predicted state values and a second number of specific values in the state values; determines a monitoring threshold based on the classification data indicator, and monitors newly added investment transactions according to the monitoring threshold. This can greatly reduce manpower and time costs and improve the investment research efficiency of bank wealth management.

[0099] In another embodiment, the investment transaction monitoring device based on the investment research report can be configured separately from the central processor 9100. For example, the investment transaction monitoring based on the investment research report can be configured as a chip connected to the central processor 9100, and the investment transaction monitoring function based on the investment research report can be realized through the control of the central processor.

[0100] like Figure 6 As shown, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Figure 6 In addition, the electronic device 9600 may also include all components shown in Figure 6 For components not shown, reference may be made to the prior art.

[0101] like Figure 6 As shown, the central processing unit 9100 is sometimes also referred to as a controller or operation control, and may include a microprocessor or other processor device and / or logic device. The central processing unit 9100 receives input and controls the operation of various components of the electronic device 9600.

[0102] Memory 9140 can be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It can store the aforementioned failure-related information and also store programs that execute the relevant information. The CPU 9100 can execute the programs stored in memory 9140 to implement information storage or processing.

[0103] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 may be, for example, a keypad or touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display objects such as images and text. The display may be, for example, an LCD display, but is not limited thereto.

[0104] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), or a SIM card. Alternatively, it may be a memory that retains information even when power is off, can be selectively erased, and is provided with more data. Examples of such memory are sometimes referred to as EPROMs. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142 for storing application programs and function programs or processes for executing the operation of the electronic device 9600 by the central processing unit 9100.

[0105] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various driver programs for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0106] The communication module 9110 is a transmitter / receiver 9110 that transmits and receives signals via an antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as in a conventional mobile communication terminal.

[0107] Based on different communication technologies, multiple communication modules 9110 can be provided in the same electronic device, such as a cellular network module, a Bluetooth module, and / or a wireless local area network module. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby implementing common telecommunication functions. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. Furthermore, the audio processor 9130 is also coupled to the central processing unit 9100, enabling local recording via the microphone 9132 and playback of stored audio via the speaker 9131.

[0108] An embodiment of the present invention further provides a computer-readable storage medium capable of implementing all steps of the investment transaction monitoring method based on investment research reports in the above embodiment. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the computer program implements all steps of the investment transaction monitoring method based on investment research reports in the above embodiment. For example, when the processor executes the computer program, the following steps are implemented:

[0109] Acquire investment research report data, and extract N key data from the investment research report data based on preset key event factors; input the N key data into a preset recurrent neural network model to obtain a state value corresponding to each key data; input M key data whose state values are specific values into a preset recurrent neural network model to obtain a predicted state value corresponding to each key data; determine a classification data indicator based on a first number of specific values in the predicted state values and a second number of specific values in the state values; determine a monitoring threshold based on the classification data indicator, and monitor new investment transactions according to the monitoring threshold.

[0110] As can be seen from the above description, the computer-readable storage medium provided by the embodiment of the present invention obtains investment research report data, extracts N key data from the investment research report data based on preset key event factors; inputs the N key data into a preset recurrent neural network model to obtain a state value corresponding to each key data; inputs M key data whose state values are specific values into the preset recurrent neural network model to obtain a predicted state value corresponding to each key data; determines a classification data indicator based on a first number of specific values in the predicted state values and a second number of specific values in the state values; determines a monitoring threshold based on the classification data indicator, and monitors newly added investment transactions according to the monitoring threshold. This can greatly reduce manpower and time costs and improve the investment research efficiency of bank wealth management.

[0111] Although the present invention provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-creative work. The order of steps listed in the embodiments is only one way of executing the steps among many steps and does not represent the only execution order. When an actual device or client product is executed, the method can be executed sequentially or in parallel according to the embodiments or the accompanying drawings (for example, in a parallel processor or multi-threaded processing environment).

[0112] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, devices (systems), or computer program products. Thus, the embodiments of this specification may take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0113] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0114] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0115] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0116] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention is not limited to any single aspect, nor to any single embodiment, nor to any combination and / or permutation of these aspects and / or embodiments. Moreover, each aspect and / or embodiment of the present invention can be used alone or in combination with one or more other aspects and / or embodiments thereof.

[0117] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and description of the present invention.

Claims

1. A method for monitoring investment transactions based on investment research reports, characterized in that: include: Obtain investment research report data, and extract N key data from the investment research report data based on preset key event factors; Input N key data into the preset recurrent neural network model to obtain the state value corresponding to each key data; Inputting M key data whose state values are specific values into a preset recurrent neural network model to obtain a predicted state value corresponding to each key data, wherein the state value corresponding to each key data output by the recurrent neural network model is passed to the softmax function for classification according to the classification task; determining a classification data indicator based on a first number of specific values in the predicted state values and a second number of specific values in the state values; Determining a monitoring threshold based on the classification data indicator, and monitoring new investment transactions according to the monitoring threshold; Wherein, N and M are positive integers greater than 1, and N is greater than M; Determining a monitoring threshold based on the classification data indicator includes: According to the difference threshold corresponding to the classification data indicator, the monitoring threshold is calculated based on the classification data indicator and the difference threshold; The monitoring of the newly added investment transactions according to the monitoring threshold includes: Determine the classification data indicator corresponding to the newly added investment transaction. If the classification data indicator corresponding to the newly added investment transaction is not within the monitoring threshold range, perform early warning processing on the newly added investment transaction.

2. The investment transaction monitoring method based on investment research reports according to claim 1, characterized in that: After obtaining the investment research report data, it also includes: If it is determined that the investment research report data is unstructured data, the unstructured investment research report data is converted into semi-structured investment research report data.

3. The investment transaction monitoring method based on investment research reports according to claim 1, characterized in that: The determining of the classification data indicator based on the first number of specific values in the predicted state value and the second number of specific values in the state value includes: Four arithmetic operations are performed according to the first quantity and the second quantity, and results of the four arithmetic operations are determined as classification data indicators.

4. An investment transaction monitoring device based on investment research reports, characterized in that: include: An extraction module is used to obtain investment research report data and extract N key data from the investment research report data based on preset key event factors; The prediction module is used to input N key data into the preset recurrent neural network model to obtain the state value corresponding to each key data; Inputting M key data whose state values are specific values into a preset recurrent neural network model to obtain a predicted state value corresponding to each key data, wherein the state value corresponding to each key data output by the recurrent neural network model is passed to the softmax function for classification according to the classification task; an indicator module for determining a classification data indicator based on a first number of specific values in the predicted state values and a second number of specific values in the state values; A monitoring module, configured to determine a monitoring threshold based on the classification data indicator, and monitor new investment transactions according to the monitoring threshold; Wherein, N and M are positive integers greater than 1, and N is greater than M; The monitoring module includes: a calculation unit, configured to calculate, according to the difference threshold corresponding to the classification data indicator, the monitoring threshold based on the classification data indicator and the difference threshold; The monitoring module includes: The early warning unit is used to determine the classification data index corresponding to the newly added investment transaction, and if the classification data index corresponding to the newly added investment transaction is not within the monitoring threshold range, perform early warning processing on the newly added investment transaction.

5. The investment transaction monitoring device based on investment research reports according to claim 4, characterized in that: Also includes: The conversion module is used to convert the unstructured investment research report data into semi-structured investment research report data if it is determined that the investment research report data is unstructured data.

6. The investment transaction monitoring device based on investment research reports according to claim 4, characterized in that: The indicator module includes: A calculation unit is used to perform four arithmetic operations according to the first quantity and the second quantity, and determine the results of the four arithmetic operations as a classification data indicator.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the investment transaction monitoring method based on investment research reports described in any one of claims 1 to 3 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the investment transaction monitoring method based on investment research reports described in any one of claims 1 to 3 are implemented.

Images