Quotation method, device, equipment, storage medium and program product

Abstract

The present disclosure provides a method for providing a quotation, relating to the technical field of artificial intelligence. The method for providing a quotation comprises: obtaining a current transaction dialogue and extracting transaction basic information therefrom; respectively analyzing transaction demand analysis on the current transaction dialogue based on a large corpus and a small corpus, the small corpus comprising a corpus constructed for an initiator of the current transaction dialogue; calculating a group stability index of the small corpus according to a historical analysis result of the small corpus; determining at least one of the large corpus and the small corpus as a target corpus according to the group stability index; and generating a reference quotation matched with the current transaction dialogue according to the transaction basic information and a current analysis result of the target corpus. The present disclosure also provides a device for providing a quotation, equipment, a storage medium and a program product.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and more specifically to a pricing method, apparatus, device, storage medium, and program product. Background Technology

[0002] Natural Language Processing (NLP) technology is the identification and processing of various forms of language expression. NLP enables computers to understand the meaning of human language. Specifically, this process involves a series of operations and processing by computers, including inputting, outputting, recognizing, analyzing, understanding, and generating characters, words, and sentences, thus accelerating information transmission and cognitive activities.

[0003] Currently, natural language recognition technology can be applied in the financial field to identify user needs from transaction dialogues and then provide corresponding services to users.

[0004] In financial market transactions, the demand side typically initiates a transaction request, the service provider responds, and the demand side chooses the most satisfactory response from various service providers to complete the transaction. This process requires accurate and rapid identification of the elements in the dialogue during the transaction. However, traditional solutions generally rely on large corpora containing massive amounts of language for natural language recognition, and the accuracy and speed of the recognition results are often insufficient for practical needs. Summary of the Invention

[0005] In view of the above problems, this disclosure provides a pricing method, apparatus, device, storage medium, and program product.

[0006] According to a first aspect of this disclosure, a pricing method is provided, comprising:

[0007] Retrieve the current transaction conversation and extract basic transaction information from it;

[0008] The transaction demand analysis of the current transaction dialogue is performed based on the analysis of a large corpus and a small corpus, wherein the small corpus includes a corpus constructed for the initiator of the current transaction dialogue.

[0009] Based on the historical analysis results of the small corpus, the population stability index of the small corpus is calculated;

[0010] Based on the group stability index, at least one of the large corpus and the small corpus is determined as the target corpus;

[0011] Based on the transaction information and the current analysis results of the target corpus, a reference quote matching the current transaction dialogue is generated.

[0012] According to embodiments of this disclosure, calculating the population stability index of the small corpus based on historical analysis results of the small corpus includes:

[0013] When the group stability index is higher than the first threshold, the corpus of the small corpus is removed from the TN time period, where T is the moment when the group stability index is higher than the first threshold and N is the preset removal duration.

[0014] When the group stability index is higher than the second threshold, the large corpus is determined to be the target corpus, where the first threshold is lower than the second threshold.

[0015] According to embodiments of this disclosure, determining at least one of the large corpus and the small corpus as the target corpus based on the group stability index includes:

[0016] When the population stability index is less than the second threshold

[0017] Obtain the current analysis results of the small corpus and the current analysis results of the large corpus;

[0018] When the current analysis result of the small corpus includes valid information, the small corpus is determined as the target corpus; when the current analysis result of the large corpus includes the valid information, the current analysis result of the large corpus is used as a reference result.

[0019] When the population stability index is greater than the second threshold

[0020] Obtain the current analysis results of the large corpus;

[0021] When the current analysis results of the large corpus include the valid information, the large corpus is determined to be the target corpus.

[0022] The valid information includes at least one of the following: trading instrument, trading direction, trading period, and trading amount.

[0023] According to embodiments of this disclosure, determining at least one of the large corpus and the small corpus as the target corpus based on the group stability index further includes:

[0024] When the population stability index of the small corpus is higher than the second threshold, the current analysis result of the small corpus is obtained;

[0025] When the current analysis results of the small corpus are consistent with the current analysis results of the large corpus, the population stability index of the small corpus is reduced.

[0026] According to embodiments of this disclosure, the basic transaction information includes trader information, trading institution information, and transaction initiation time;

[0027] The step of generating a reference quote matching the current transaction dialogue based on the transaction basic information and the current analysis results of the target corpus includes:

[0028] Obtain the transaction requirements analyzed based on the target corpus to obtain the current analysis results of the target corpus;

[0029] The obtained transaction demand, trader information, trading institution information, and transaction initiation time are compared with a preset rule base to generate transaction priority, transaction amount, and reference quote.

[0030] According to embodiments of this disclosure, comparing the acquired transaction demand, trader information, trading institution information, and transaction initiation time with a preset rule base to generate transaction priority, transaction amount, and reference quote includes:

[0031] When the institution information is verified through the blacklist, it is determined whether the transaction amount in the current transaction dialogue matches the available credit limit corresponding to the transaction institution information;

[0032] The target transaction amount is determined based on the matching results;

[0033] Obtain the historical transaction success rate corresponding to the trader information;

[0034] The transaction priority is determined based on the transaction initiation time, the transaction institution information, and the historical transaction success rate.

[0035] According to embodiments of this disclosure, comparing the acquired transaction demand, trader information, trading institution information, and transaction initiation time with a preset rule base to generate transaction priority, transaction amount, and reference quote includes:

[0036] Obtain multiple target transaction amounts generated within a preset time period, where different target transaction amounts belong to different current transaction conversations;

[0037] The obtained target transaction amounts are weighted and averaged to obtain the real-time average transaction amount;

[0038] The reference price is adjusted based on the real-time average transaction amount, the current balance of products to be traded, the current balance of funds, and the acceptance frequency of the reference price.

[0039] A second aspect of this disclosure provides a pricing device, comprising:

[0040] The extraction module is used to obtain the current transaction dialogue and extract basic transaction information from it;

[0041] The semantic recognition module is used to analyze the current transaction dialogue based on a large corpus and a small corpus respectively to perform transaction demand analysis. The small corpus includes a corpus constructed for the initiator of the current transaction dialogue.

[0042] The calculation module is used to calculate the population stability index of the small corpus based on the historical analysis results of the small corpus.

[0043] An evaluation module is used to determine at least one of the large corpus and the small corpus as the target corpus based on the group stability index.

[0044] The quote generation module is used to generate a reference quote that matches the current transaction dialogue based on the basic transaction information and the current analysis results of the target corpus.

[0045] A third aspect of this disclosure provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors perform the above-described quoting method.

[0046] A fourth aspect of this disclosure also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the above-described quoting method.

[0047] The fifth aspect of this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described quoting method.

[0048] The above one or more embodiments have the following advantages or benefits:

[0049] The pricing method of the embodiments of this disclosure can achieve faster and more accurate natural language recognition by establishing a small corpus for trading counterparties. Furthermore, the pricing method of the embodiments of this disclosure evaluates the credibility of the small corpus through a group stability index. When the credibility of the small corpus decreases due to changes in the trading habits or business of the trading counterparties, it can be switched back to a large corpus in a timely manner, and natural language recognition can be performed based on the large corpus, thereby ensuring that the accuracy of language recognition does not decrease. Attached Figure Description

[0050] The foregoing contents, as well as other objects, features, and advantages of this disclosure, will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0051] Figure 1 The illustrations depict application scenarios of the pricing method, apparatus, system, storage medium, and program product according to embodiments of the present disclosure.

[0052] Figure 2 A flowchart illustrating a pricing method according to an embodiment of the present disclosure is shown schematically;

[0053] Figure 3 A flowchart illustrating the updating of a small corpus according to an embodiment of this disclosure is shown schematically;

[0054] Figure 4 One of the flowcharts for determining a target corpus according to an embodiment of the present disclosure is illustrated schematically;

[0055] Figure 5 A second flowchart illustrating the determination of a target corpus according to an embodiment of the present disclosure is shown schematically.

[0056] Figure 6 A flowchart illustrating the determination of a target corpus according to an embodiment of the present disclosure is shown in the schematic diagram.

[0057] Figure 7 A flowchart illustrating the generation of a reference quote according to an embodiment of the present disclosure is shown schematically;

[0058] Figure 8 A flowchart illustrating the generation of transaction priority and transaction amount according to an embodiment of this disclosure is shown schematically;

[0059] Figure 9 A flowchart illustrating the generation of an adjusted reference quote according to an embodiment of the present disclosure is shown schematically;

[0060] Figure 10 A schematic block diagram of a pricing device according to an embodiment of the present disclosure is shown.

[0061] Figure 11 A block diagram schematically illustrates an electronic device suitable for implementing a quoting method according to an embodiment of the present disclosure. Detailed Implementation

[0062] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0063] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0064] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0065] When using expressions such as "at least one of A, B, and C", they should generally be interpreted in accordance with the meaning that is commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0066] It should be noted that the pricing method, apparatus, system, storage medium, and program product provided in the embodiments of this disclosure relate to the field of artificial intelligence technology. The pricing method, apparatus, system, storage medium, and program product provided in the embodiments of this disclosure can be applied to the financial field or any field other than finance. The embodiments of this disclosure do not limit the application areas of the pricing method, apparatus, system, storage medium, and program product.

[0067] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision, disclosure, and application of user personal information comply with the provisions of relevant laws and regulations, necessary confidentiality measures have been taken, and there is no violation of public order and good morals.

[0068] Embodiments of this disclosure provide a pricing method, comprising: acquiring a current transaction dialogue and extracting basic transaction information therefrom; performing transaction demand analysis on the current transaction dialogue based on a large corpus and a small corpus, wherein the small corpus includes a corpus constructed for the initiator of the current transaction dialogue; calculating a group stability index of the small corpus based on historical analysis results of the small corpus; determining at least one of the large corpus and the small corpus as a target corpus based on the group stability index; and generating a reference price matching the current transaction dialogue based on the basic transaction information and the current analysis results of the target corpus.

[0069] The pricing method of the embodiments of this disclosure can achieve faster and more accurate natural language recognition by establishing a small corpus for trading counterparties. Furthermore, the pricing method of the embodiments of this disclosure evaluates the credibility of the small corpus through a group stability index. When the credibility of the small corpus decreases due to changes in the trading habits or business of the trading counterparties, it can be switched back to a large corpus in a timely manner, and natural language recognition can be performed based on the large corpus, thereby ensuring that the accuracy of language recognition does not decrease.

[0070] Figure 1 The illustrations depict application scenarios of the pricing method, apparatus, system, storage medium, and program product according to embodiments of the present disclosure.

[0071] like Figure 1 As shown, application scenario 100 according to this embodiment may include terminal devices 101, 102, and 103, network 104, and server 105. Network 104 is used as a medium to provide a communication link between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0072] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0073] Terminal devices 101, 102, and 103 can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0074] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using terminal devices 101, 102, and 103 (for example only). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0075] It should be noted that the pricing method provided in this embodiment can generally be executed by server 105. Correspondingly, the pricing device provided in this embodiment can generally be located in server 105. The pricing method provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105. Correspondingly, the pricing device provided in this embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105.

[0076] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0077] The following will be based on Figure 1 The described scene, through Figures 2-9 The quotation method of the disclosed embodiments will be described in detail.

[0078] Figure 2 A flowchart illustrating a pricing method according to an embodiment of the present disclosure is shown schematically.

[0079] like Figure 2 As shown, the quotation method in this embodiment includes steps S210 to S250. It should be noted that, although Figure 2 The steps in the diagram are shown sequentially as indicated by the arrows; however, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise explicitly stated herein, there is no strict order constraint on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the diagram may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0080] In step S210, the current transaction dialogue is obtained, and basic transaction information is extracted from it.

[0081] In the embodiments of this disclosure, a transaction dialogue can refer to a conversation between multiple parties involved in a transaction within a market scenario. For example, one of the multiple parties (e.g., party A) proposes a transaction, and other parties (e.g., party B) can provide quotes based on this transaction. Party A can then choose a suitable party to complete the transaction based on the quotes from the other parties. In this scenario, the transaction dialogue can include basic transaction information of at least one party, such as trader information, information about the trading institution to which the trader belongs, etc. The current transaction dialogue is the transaction dialogue generated in the current transaction.

[0082] The pricing method in the embodiments of this disclosure is applied to party B, and aims to provide an automatic method for generating accurate and reasonable pricing for party A. In the above scenario, party B is the counterparty to party A, and correspondingly, party B is the counterparty to party A. For clarity, the embodiments of this disclosure will be described from the perspective of party B below. Therefore, unless otherwise specified, the counterparty in the following text refers to party A.

[0083] In step S220, transaction demand analysis is performed on the current transaction dialogue based on the large corpus and the small corpus respectively. The small corpus includes a corpus constructed for the initiator of the current transaction dialogue.

[0084] In the embodiments of this disclosure, a large corpus can refer to a general corpus containing massive amounts of data. Besides being used for semantic recognition of transaction dialogues in these embodiments, a large corpus can also be used for semantic recognition in other business applications. A small corpus can refer to a corpus specific to a particular target, such as a corpus specific to a trading counterparty. A small corpus can store data related to historical transactions with a trading counterparty, thus forming a personalized corpus tailored to that counterparty. Compared to a large corpus, a small corpus offers more granularity, which is beneficial for accurately identifying the trading counterparty's needs, such as their preferences regarding transaction amounts and pricing. Furthermore, semantic recognition based on a small corpus is faster, enabling quicker responses to transaction dialogues.

[0085] In the embodiments of this disclosure, performing transaction demand analysis on the current transaction dialogue based on both a large corpus and a small corpus specifically means using natural language processing techniques to perform semantic recognition on the current transaction dialogue based on both the large and small corpora, thereby extracting the transaction demands of the counterparty. In other words, in the embodiments of this disclosure, semantic recognition of the transaction dialogue can be performed once based on the large corpus and simultaneously once based on the small corpus.

[0086] In step S230, the population stability index of the small corpus is calculated based on the historical analysis results of the small corpus.

[0087] In the embodiments of this disclosure, the historical analysis results of the small corpus may refer to the transaction demands identified from historical transaction dialogues based on the small corpus. Historical transaction dialogues may refer to several transaction dialogues that occurred before the current transaction dialogue. Transaction demands may include, for example, the transaction type, transaction direction, transaction period, and transaction amount identified from a transaction dialogue.

[0088] In the embodiments of this disclosure, the credibility of a small corpus can be evaluated. Specifically, the Population Stability Index (PSI) of the small corpus can be calculated based on the accuracy of historical analysis results, and the credibility of the small corpus can be determined based on the calculated PSI value.

[0089] The group stability index can be calculated in the following ways:

[0090] PSI=sum[(Ac-Ex)*ln(Ac / Ex)];

[0091] Where Ac represents the proportion of sample data in the actual data, and Ex represents the proportion of sample data in the expected data. Generally, when the PSI value is greater than or equal to 0.25, the small corpus is considered unstable. Of course, this embodiment of the present disclosure does not limit this preset condition. Through this calculation method, the reliability of the small corpus can be quickly measured with relatively small computational overhead, which is beneficial for timely switching between large and small corpora in subsequent steps.

[0092] In step S240, at least one of the large corpus and the small corpus is selected as the target corpus based on the group stability index.

[0093] In the embodiments of this disclosure, the lower the value of the group stability index, the higher the reliability of the small corpus. For example, when the group stability index reaches a preset value, it can be determined that the small corpus is suitable for analyzing the trading needs of counterparties. In this case, the small corpus can be used as the target corpus, and then a reference quote can be generated based on the current analysis results of the small corpus, thereby generating a personalized reference quote for counterparties and improving the quote hit rate. Specifically, the current analysis results of the small corpus refer to the trading needs identified from the current trading dialogue based on the small corpus. When the group stability index does not reach the preset value, it can be determined that the small corpus cannot yet be used to analyze the trading needs of counterparties (possibly due to changes in the counterparty's trading habits or trading business). In this case, a large corpus can be used as the target corpus, and then a reference quote can be generated based on the current analysis results of the large corpus, thereby ensuring the validity of the final generated reference quote. Specifically, the current analysis results of the large corpus refer to the trading needs identified from the current trading dialogue based on the large corpus.

[0094] In step S250, a reference quote matching the current transaction dialogue is generated based on the basic transaction information and the current analysis results of the target corpus.

[0095] In embodiments of this disclosure, the current analysis result of the target corpus may refer to the transaction requirements identified from the current transaction dialogue based on the target corpus (large corpus and / or small corpus). Furthermore, the basic transaction information and the transaction requirements identified by the target corpus can be compared with preset rules in the first rule base to provide a reference quote matching the current transaction dialogue.

[0096] In summary, the pricing method of this disclosure achieves faster and more accurate natural language recognition by establishing a small corpus oriented towards trading counterparties. Furthermore, the pricing method uses a group stability index to evaluate the reliability of the small corpus. When the reliability of the small corpus decreases due to changes in the trading habits or business of the trading counterparties, it can promptly switch back to a large corpus and perform natural language recognition based on the large corpus, thus ensuring that the accuracy of language recognition does not decrease. Moreover, the recognition results obtained in this way are beneficial for analyzing and generating reference prices, thereby making the generation of reference prices more efficient and accurate.

[0097] The following is combined Figures 2 to 9 The pricing method of this disclosure will be further described.

[0098] Figure 3 A flowchart illustrating the updating of a small corpus according to an embodiment of this disclosure is shown schematically.

[0099] like Figure 3 As shown, in some specific embodiments, step S230 includes steps S231 and S232.

[0100] In step S231, when the group stability index is higher than the first threshold, the corpus data within the TN time period in the small corpus is removed, where T is the time when the group stability index is higher than the first threshold, and N is the preset removal duration. Otherwise, the small corpus can be determined as the target corpus, and step S240 is executed.

[0101] In the embodiments of this disclosure, when the group stability index increases, it can be attributed to changes in the counterparty's trading habits or business practices. For example, changes in the counterparty's trading habits or business practices can lead to significant deviations between the content of the current trading dialogue and the existing data in the small corpus (e.g., historical trading dialogues), resulting in a decrease in the semantic recognition accuracy of the small corpus. Therefore, when the group stability index increases, some older data in the small corpus can be removed, specifically data from the TN time period, thereby improving the semantic recognition accuracy.

[0102] Optionally, the step of removing old data can be performed in stages. For example, the removal process can be divided into multiple sub-steps. In each sub-step, old data from a short period of time is removed backward from a certain point in time. After each removal, the group stability index is calculated. When the group stability index rises and reaches the expected level, the removal step can be stopped. For example, after removing data from time period Tn, the group stability index can be calculated. If the calculated group stability index is still high, the old data can be removed backward from time point n until the group stability index rises and reaches the expected level. Here, time point n is after time point N.

[0103] Therefore, by setting a first threshold, when the group stability index of the small corpus rises but has not yet risen to a high value that makes the small corpus unreliable, the corpus in the small corpus can be updated in a timely manner, so that the small corpus can adapt to the changes of its corresponding trading counterpart in real time.

[0104] In step S232, if the group stability index is higher than the second threshold, the large corpus is determined as the target corpus, and the first threshold is lower than the second threshold. Otherwise, the small corpus can be determined as the target corpus.

[0105] In the embodiments of this disclosure, the second threshold can be a reference value used to determine the reliability of the small corpus. When the group stability index of the small corpus is lower than the second threshold, it indicates that the reliability of the small corpus is acceptable. Therefore, when generating a reference quote in subsequent steps, the current analysis results based on the small corpus can be accepted. In this way, the reliability of the small corpus can be quickly determined with low computational resource consumption, thereby realizing the switching between large and small corpora to ensure the best semantic recognition effect in the current scenario.

[0106] Figure 4 One of the flowcharts for determining a target corpus according to an embodiment of the present disclosure is illustrated schematically.

[0107] like Figure 4 As shown, in some specific embodiments, when the population stability index is lower than the second threshold, step S240 includes steps S241 and S242.

[0108] In step S241, the current analysis results of the small corpus and the current analysis results of the large corpus are obtained.

[0109] In the embodiments of this disclosure, in step S220, the transaction requirements in the current transaction dialogue are analyzed based on a large corpus and a small corpus. Therefore, in step S241, the transaction requirements analyzed based on the large corpus in step S220 can be obtained to obtain the current analysis result based on the large corpus; and the transaction requirements analyzed based on the small corpus in step S220 can be obtained to obtain the current analysis result based on the small corpus.

[0110] In step S242, if the current analysis result of the small corpus includes valid information, the small corpus is determined as the target corpus; if the current analysis result of the large corpus includes valid information, the current analysis result of the large corpus is used as the reference result. Valid information includes at least one of the following: trading instrument, trading direction, trading period, and trading amount. Otherwise, the current trading dialogue can be broken down into short sentences, and the above steps can be repeated.

[0111] In other words, when the small corpus has high reliability and can identify at least one of the following transaction requirements from the current transaction dialogue: transaction type, transaction direction, transaction period, and transaction amount, the small corpus can be designated as the target corpus, and the transaction requirements identified by the small corpus will be used as the basis for generating reference quotes. Thus, through a double verification process, the validity and reliability of the small corpus are ensured, and subsequent operations are performed based on this valid and reliable corpus.

[0112] As mentioned earlier, when the group stability index of the small corpus is lower than the first threshold, it indicates that the small corpus has high credibility. However, in order to ensure that the generated reference quote is comprehensive and reliable, the current analysis results of the large corpus are still obtained and used as reference results. At this time, while generating a reference quote based on the current analysis results of the small corpus, an alternative quote can also be generated based on the current analysis results of the large corpus. Then, the reference quote and the alternative quote are provided to the trader at the same time so that the trader can select, confirm and send them to the counterparty.

[0113] When the group stability index of the small corpus is higher than the second threshold, it indicates that the credibility of the small corpus is too low. Therefore, when generating a reference quote in subsequent steps, the current analysis results based on the small corpus will not be accepted, but the current analysis results based on the large corpus will be accepted instead.

[0114] Figure 5 A second flowchart illustrating the determination of a target corpus according to an embodiment of the present disclosure is shown schematically.

[0115] like Figure 5 As shown, in some specific embodiments, when the population stability index is higher than the second threshold, step S240 includes steps S243 and S244.

[0116] In step S243, the current analysis results of the large corpus are obtained.

[0117] In the embodiments of this disclosure, in step S220, the transaction requirements in the current transaction dialogue are analyzed based on the large corpus. Therefore, in step S243, the transaction requirements analyzed from the current transaction dialogue based on the large corpus in step S220 can be obtained to obtain the current analysis results of the large corpus.

[0118] In step S244, if the current analysis results of the large corpus contain valid information, then the large corpus is determined to be the target corpus. Otherwise, the current transaction dialogue can be broken down into short sentences, and the above steps can be repeated.

[0119] In this way, when the reliability of the small corpus is low, the judgment is made on whether the output of the large corpus meets the expectations. That is, whether the large corpus can identify valid information from the current transaction dialogue, including at least one of the transaction varieties, transaction direction, transaction period and transaction amount. When both of these conditions are met, the large corpus is determined as the target corpus, and the transaction demand identified by the large corpus is used as the basis for generating reference quotes. This ensures that the accuracy of the data source when generating reference quotes will not decrease due to changes in business scenarios or transaction habits.

[0120] Figure 6A flowchart illustrating the determination of a target corpus according to an embodiment of the present disclosure is shown in Figure 3.

[0121] like Figure 6 As shown, in some specific embodiments, step S240 further includes steps S245 and S246.

[0122] In step S245, when the population stability index of the small corpus is higher than the second threshold, the current analysis result of the small corpus is obtained.

[0123] In the embodiments of this disclosure, after obtaining the current analysis results of the small corpus, the small corpus can be corrected by comparing the current analysis results of the small corpus with the current analysis results of the large corpus.

[0124] Specifically, in step S246, when the current analysis results of the small corpus are consistent with the current analysis results of the large corpus, the group stability index of the small corpus is reduced. This can improve the credibility of the small corpus in a timely manner, thereby enabling timely switching back to the small corpus and performing semantic recognition based on the small corpus as much as possible to improve processing efficiency and accuracy.

[0125] When the current analysis results based on the small corpus are inconsistent with the current analysis results based on the large corpus, the current analysis results of the small corpus can be returned, and the small corpus can be iterated to update the relevant parameters of the small corpus until the current analysis results of the small corpus can meet the expectations.

[0126] Figure 7 A flowchart illustrating the generation of a reference quote according to an embodiment of the present disclosure is shown schematically.

[0127] like Figure 7 As shown, in some specific embodiments, the basic transaction information includes trader information, trading institution information, and transaction initiation time.

[0128] Step S250 includes steps S251 and S252.

[0129] In step S251, the transaction requirements analyzed based on the target corpus are obtained.

[0130] In step S252, the obtained transaction demand, trader information, trading institution information and transaction initiation time are compared with the preset rule base to generate transaction priority, transaction amount and reference price.

[0131] In the embodiments of this disclosure, multiple transaction dialogues may occur at the same time period. Different transaction dialogues correspond to different initiators and transaction amounts of a single transaction. Through the above method, transaction priority and transaction amount are generated for a single transaction corresponding to each transaction dialogue. In this way, while generating reference quotes, reasonable allocation of resources can also be achieved.

[0132] In the embodiments of this disclosure, the transaction demand analyzed from the target corpus is at least one of the following: transaction type, transaction direction, transaction period, and transaction amount analyzed from the current transaction dialogue. This information, along with basic transaction information, is then aggregated and compared with at least one rule in a preset rule base to generate the transaction priority and transaction amount corresponding to the current transaction dialogue. For example, a transaction initiated earlier and whose institutional information indicates that the institution is more important will have a higher transaction amount and priority.

[0133] Figure 8 A flowchart illustrating the generation of transaction priorities and transaction amounts according to an embodiment of this disclosure is shown.

[0134] like Figure 8 As shown, in some specific embodiments, step S252 includes steps S2521 to S2524.

[0135] In step S2521, when the institution information passes the blacklist verification, it is determined whether the transaction amount matches the available credit limit corresponding to the institution information. If the institution information fails the blacklist verification, a failure explanation is returned. At this point, the next step can be executed according to the trader's operation.

[0136] In step S2522, the target transaction amount is determined based on the matching results.

[0137] In the embodiments disclosed herein, the authorized limit varies for different counterparties. For example, counterparty Z1, with good credit, will have a higher authorized limit, while counterparty Z2, with poor credit, will have a lower authorized limit. Therefore, the transaction limit in the current transaction conversation can be obtained. If the authorized limit of the initiator of the current transaction conversation is greater than or equal to the transaction limit in the current transaction conversation, then the transaction limit in the current transaction conversation is used as the target transaction limit; otherwise, the authorized limit is used as the target transaction limit.

[0138] In step S2523, the historical transaction success rate corresponding to the trader information is obtained. The trader information can refer to information that identifies the counterparty, and through this identification information, historical transactions related to that counterparty can be obtained, thereby acquiring the historical transaction success rate.

[0139] In step S2524, the transaction priority is determined based on the transaction initiation time, transaction institution information, and historical transaction success rate.

[0140] In the embodiments of this disclosure, multiple transaction dialogues may occur within the same time period, with different initiators for each dialogue. Using the method described above, a transaction priority is generated for each dialogue and the corresponding transaction. Therefore, a quote can be sent first to the initiator of the transaction with the higher priority, ensuring the rational use of resources. For example, transactions initiated earlier have higher priority, transactions from institutions whose information indicates their importance have higher priority, transactions with higher historical success rates have higher priority, and so on. Of course, these factors can also be combined, and the weight of each factor can be determined according to actual needs; no restrictions are placed here. In this way, existing blacklist systems and historical data (such as historical success rates) can be reused, thereby accurately determining transaction priorities without adding additional data acquisition operations.

[0141] Figure 9 A flowchart illustrating the generation of an adjusted reference quote according to an embodiment of this disclosure is shown schematically.

[0142] like Figure 9 As shown, in some specific embodiments, step S252 further includes steps S2525 to S2527.

[0143] In step S2525, multiple target transaction amounts generated within a preset time period are obtained, and different target transaction amounts belong to different current transaction dialogues.

[0144] In the embodiments of this disclosure, each transaction may correspond to at least one transaction dialogue, and the target transaction amount for each transaction can be derived from the corresponding transaction dialogue in the manner described above. The preset time period may include a time range before and after the current time point.

[0145] In step S2526, the obtained target transaction amounts are weighted and averaged to obtain the real-time average transaction amount.

[0146] In step S2527, the reference price is adjusted based on the real-time average transaction amount, the current balance of products to be traded, the current balance of funds, and the acceptance frequency of the reference price.

[0147] The quotation method of the present disclosure can be applied to interbank market transactions. In this scenario, the reference quotation may refer to the interest rate of a financial product. Step S2526 may specifically involve adding or subtracting spreads on the interest rate to adjust the reference quotation.

[0148] In this way, a comprehensive analysis can be conducted based on the current scenario and multiple target transaction amounts. For example, the average transaction amount can be used as a reference for resource allocation, and the reference price can be adjusted accordingly, such as by raising or lowering it. This allows for real-time optimization of the generation of reference prices, making them as close as possible to the optimal result in the current scenario and improving the accuracy of generation.

[0149] The embodiments of this disclosure provide a solution for automatically generating quotes by introducing a small corpus, which overcomes the problem that existing interbank market dialogue and quoting methods require traders to perform a large amount of repetitive work. It can quickly and accurately respond to market trading needs and play a certain role in complex scenarios such as risk control and intelligent trading.

[0150] In the embodiments of this disclosure, the semantic recognition process described above can be implemented using the hierarchical softmax of the CBOW model of word2Vec, thereby predicting the actual meaning expressed based on the trading dialogue of the trading counterparty, corresponding to dimensions such as trading instrument, trading direction, trading period, and trading amount.

[0151] In the embodiments of this disclosure, after the reference quote is sent to the counterparty, if the counterparty returns confirmation of the transaction, the transaction confirmation process is triggered. At this time, the transaction confirmation process of the transaction center system and the transaction bookkeeping process of the bank system can be triggered by RPA technology. After completion, the transaction is handed over to the back office for accounting and settlement processing.

[0152] Based on the above-described pricing method, this disclosure also provides a pricing device. The following will be combined with... Figure 10 The device is described in detail.

[0153] Figure 10 A schematic block diagram of a pricing device according to an embodiment of the present disclosure is shown.

[0154] like Figure 10 As shown, the quotation device 1000 of this embodiment includes an extraction module 1010, a semantic recognition module 1020, a calculation module 1030, an evaluation module 1040, and a quotation generation module 1050.

[0155] The extraction module 1010 is used to obtain the current transaction dialogue and extract basic transaction information from it. In one embodiment, the extraction module 1010 can be used to perform step S210 described above, which will not be repeated here.

[0156] The semantic recognition module 1020 is used to analyze the current transaction dialogue based on a large corpus and a small corpus to perform transaction demand analysis. The small corpus includes a corpus constructed for the initiator of the current transaction dialogue. In one embodiment, the semantic recognition module 1020 can be used to execute step S220 described above, which will not be repeated here.

[0157] The calculation module 1030 is used to calculate the group stability index of the small corpus based on the historical analysis results of the small corpus. In one embodiment, the calculation module 1030 can be used to perform step S230 described above, which will not be repeated here.

[0158] The evaluation module 1040 is used to determine at least one of the large corpus and the small corpus as the target corpus based on the group stability index. In one embodiment, the evaluation module 1040 can be used to perform step S240 described above, which will not be repeated here.

[0159] The quote generation module 1050 is used to generate a reference quote that matches the current transaction dialogue based on the basic transaction information and the current analysis results of the target corpus. In one embodiment, the quote generation module 1050 can be used to perform step S250 described above, which will not be repeated here.

[0160] In summary, the pricing apparatus of the embodiments of this disclosure achieves faster and more accurate natural language recognition by establishing a small corpus oriented towards trading counterparties. Furthermore, the analysis results based on the small corpus enable the rapid generation of more targeted pricing. Moreover, the pricing method of the embodiments of this disclosure evaluates the credibility of the small corpus using a group stability index. When the credibility of the small corpus decreases due to changes in the trading habits or business of the trading counterparties, it can promptly switch back to a large corpus and generate a reference pricing based on the current analysis results of the large corpus, thereby ensuring the validity of the final output reference pricing.

[0161] According to embodiments of this disclosure, any plurality of modules among the extraction module 1010, semantic recognition module 1020, calculation module 1030, evaluation module 1040, and quotation generation module 1050 may be combined into one module, or any one of these modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in one module. According to embodiments of this disclosure, at least one of the extraction module 1010, semantic recognition module 1020, calculation module 1030, evaluation module 1040, and quotation generation module 1050 may be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any one of the three implementation methods or a suitable combination of any of them. Alternatively, at least one of the extraction module 1010, semantic recognition module 1020, calculation module 1030, evaluation module 1040, and quotation generation module 1050 may be implemented at least partially as a computer program module, which can perform corresponding functions when the computer program module is run.

[0162] In some specific embodiments, the computing module 1030 is specifically used to perform the following steps:

[0163] When the group stability index is higher than the first threshold, the corpus data in the TN time period is removed from the small corpus, where T is the moment when the group stability index is higher than the first threshold and N is the preset removal duration.

[0164] When the group stability index is higher than the second threshold, the large corpus is determined as the target corpus, and the first threshold is lower than the second threshold.

[0165] In some specific embodiments, the evaluation module 1040 is specifically used to perform the following steps:

[0166] When the population stability index is less than the first threshold

[0167] Obtain the current analysis results for the small corpus and the large corpus.

[0168] When the current analysis results of the small corpus contain valid information, the small corpus is determined as the target corpus. When the current analysis results of the large corpus contain valid information, the current analysis results of the large corpus are used as the reference results.

[0169] When the population stability index is greater than the second threshold

[0170] Get the current analysis results of a large corpus.

[0171] When the current analysis results of the large corpus contain valid information, the large corpus is determined to be the target corpus.

[0172] The valid information includes at least one of the following: the trading instrument, the trading direction, the trading period, and the trading amount.

[0173] In some specific embodiments, the evaluation module 1040 is further configured to perform the following steps:

[0174] When the population stability index of the small corpus is higher than the first threshold, the current analysis results of the small corpus are obtained.

[0175] When the current analysis results of the small corpus are consistent with the current analysis results of the large corpus, the population stability index of the small corpus should be reduced.

[0176] In some specific embodiments, the basic transaction information includes trader information, trading institution information, and transaction initiation time. The quote generation module 1050 is specifically used to perform the following steps:

[0177] Obtain transaction demands based on the target corpus analysis to obtain the current analysis results of the target corpus.

[0178] The obtained transaction requests, trader information, trading institution information, and transaction initiation time are compared with the preset rule base to generate transaction priority, transaction amount, and reference quote.

[0179] In some specific embodiments, the quotation generation module 1050 is specifically used to perform the following steps:

[0180] When an institution's information is verified through the blacklist, it is determined whether the transaction amount in the current transaction conversation matches the available credit limit corresponding to the institution's information.

[0181] The target transaction amount is determined based on the matching results.

[0182] Obtain the historical success rate of trades corresponding to trader information.

[0183] The transaction priority is determined based on the transaction initiation time, transaction institution information, and historical success rate.

[0184] In some specific embodiments, the quotation generation module 1050 is specifically used to perform the following steps:

[0185] Retrieve multiple target transaction amounts generated within a preset time period; different target transaction amounts belong to different current transaction conversations.

[0186] The obtained target transaction amounts are weighted and averaged to obtain the real-time average transaction amount.

[0187] The reference quote is adjusted based on the real-time average transaction amount, the current balance of products to be traded, the current balance of funds, and the frequency of acceptance of the reference quote.

[0188] Figure 11 A block diagram schematically illustrates an electronic device suitable for implementing a quoting method according to an embodiment of the present disclosure.

[0189] like Figure 11 As shown, an electronic device 1100 according to an embodiment of the present disclosure includes a processor 1101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage portion 1108 into a random access memory (RAM) 1103. The processor 1101 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 1101 may also include onboard memory for caching purposes. The processor 1101 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0190] RAM 1103 stores various programs and data required for the operation of electronic device 1100. Processor 1101, ROM 1102, and RAM 1103 are interconnected via bus 1104. Processor 1101 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 1102 and / or RAM 1103. It should be noted that the programs may also be stored in one or more memories other than ROM 1102 and RAM 1103. Processor 1101 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0191] According to embodiments of this disclosure, the electronic device 1100 may further include an input / output (I / O) interface 1105, which is also connected to a bus 1104. The electronic device 1100 may also include one or more of the following components connected to the I / O interface 1105: an input section 1106 including a keyboard, mouse, etc.; an output section 1107 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN card, modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the I / O interface 1105 as needed. A removable medium 1111, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 1110 as needed so that computer programs read from it can be installed into the storage section 1108 as needed.

[0192] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the pricing method according to the embodiments of this disclosure.

[0193] According to embodiments of this disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this disclosure, the computer-readable storage medium may include ROM 1102 and / or RAM 1103 and / or one or more memories other than ROM 1102 and RAM 1103 described above.

[0194] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to cause the computer system to implement the quoting method provided in the embodiments of this disclosure.

[0195] When the computer program is executed by the processor 1101, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0196] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 1109, and / or installed from the removable medium 1111. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0197] In such an embodiment, the computer program can be downloaded and installed from a network via communication section 1109, and / or installed from removable medium 1111. When the computer program is executed by processor 1101, it performs the functions defined in the system of this disclosure embodiment. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0198] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0199] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0200] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0201] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A pricing method, characterized in that, include: Retrieve the current transaction conversation and extract basic transaction information from it; The transaction demand analysis of the current transaction dialogue is performed based on a large corpus and a small corpus. The small corpus includes a corpus constructed for the initiator of the current transaction dialogue, and stores the corpus of language involved in the initiator in historical transactions. Based on the historical analysis results of the small corpus, the population stability index of the small corpus is calculated; Based on the aforementioned group stability index, at least one of the large corpus and the small corpus is determined as the target corpus, including: When the population stability index is less than the second threshold Obtain the current analysis results of the small corpus and the current analysis results of the large corpus; When the current analysis result of the small corpus includes valid information, the small corpus is determined as the target corpus; when the current analysis result of the large corpus includes the valid information, the current analysis result of the large corpus is used as a reference result; wherein, the valid information includes at least one of the following: trading instrument, trading direction, trading period, and trading amount; Based on the transaction information and the current analysis results of the target corpus, a reference quote matching the current transaction dialogue is generated.

2. The quotation method according to claim 1, characterized in that, The step of calculating the population stability index of the small corpus based on the historical analysis results of the small corpus includes: When the group stability index is higher than the first threshold, the corpus in the small corpus is removed from the time period T to TN, where T is the moment when the group stability index is higher than the first threshold and N is the preset removal duration. When the group stability index is higher than the second threshold, the large corpus is determined to be the target corpus, and the first threshold is lower than the second threshold.

3. The quotation method according to claim 2, characterized in that, The step of determining at least one of the large corpus and the small corpus as the target corpus based on the group stability index includes: When the group stability index is greater than the second threshold, the current analysis result of the large corpus is obtained; When the current analysis results of the large corpus include the valid information, the large corpus is determined to be the target corpus.

4. The quotation method according to claim 2, characterized in that, The step of determining at least one of the large corpus and the small corpus as the target corpus based on the group stability index further includes: When the population stability index of the small corpus is higher than the second threshold, the current analysis result of the small corpus is obtained; When the current analysis results of the small corpus are consistent with the current analysis results of the large corpus, the population stability index of the small corpus is reduced.

5. The quotation method according to claim 1, characterized in that, The basic transaction information includes trader information, trading institution information, and transaction initiation time; The step of generating a reference quote matching the current transaction dialogue based on the transaction basic information and the current analysis results of the target corpus includes: Obtain the transaction requirements analyzed based on the target corpus to obtain the current analysis results of the target corpus; The obtained transaction demand, trader information, trading institution information, and transaction initiation time are compared with a preset rule base to generate transaction priority, transaction amount, and reference quote.

6. The quotation method according to claim 5, characterized in that, The step of comparing the acquired transaction demand, trader information, trading institution information, and transaction initiation time with a preset rule base to generate transaction priority, transaction amount, and reference quote includes: When the transaction institution information is verified through the blacklist, it is determined whether the transaction amount in the current transaction dialogue matches the available credit limit corresponding to the transaction institution information; The target transaction amount is determined based on the matching results; Obtain the historical transaction success rate corresponding to the trader information; The transaction priority is determined based on the transaction initiation time, the transaction institution information, and the historical transaction success rate.

7. The quotation method according to claim 5, characterized in that, The step of comparing the acquired transaction demand, trader information, trading institution information, and transaction initiation time with a preset rule base to generate transaction priority, transaction amount, and reference quote includes: Obtain multiple target transaction amounts generated within a preset time period, where different target transaction amounts belong to different current transaction conversations; The obtained target transaction amounts are weighted and averaged to obtain the real-time average transaction amount; The reference price is adjusted based on the real-time average transaction amount, the current balance of products to be traded, the current balance of funds, and the acceptance frequency of the reference price.

8. A quotation device, characterized in that, include: The extraction module is used to obtain the current transaction dialogue and extract basic transaction information from it; The semantic recognition module is used to perform transaction demand analysis on the current transaction dialogue based on a large corpus and a small corpus respectively. The small corpus includes a corpus constructed for the initiator of the current transaction dialogue, and the small corpus stores the corpus of language involved in the initiator in historical transactions. The calculation module is used to calculate the population stability index of the small corpus based on the historical analysis results of the small corpus. The evaluation module is used to determine at least one of the large corpus and the small corpus as the target corpus based on the group stability index, including: When the population stability index is less than the second threshold Obtain the current analysis results of the small corpus and the current analysis results of the large corpus; When the current analysis result of the small corpus includes valid information, the small corpus is determined as the target corpus; when the current analysis result of the large corpus includes the valid information, the current analysis result of the large corpus is used as a reference result; wherein, the valid information includes at least one of the following: trading instrument, trading direction, trading period, and trading amount; The quote generation module is used to generate a reference quote that matches the current transaction dialogue based on the basic transaction information and the current analysis results of the target corpus.

9. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors perform the quoting method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores executable instructions that, when executed by a processor, cause the processor to perform the quoting method according to any one of claims 1 to 7.

11. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the quoting method according to any one of claims 1 to 7.

Images